Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
See new possibilities with predictive analytics Check outnew: what’s new Check out what’s ■ SPSS 15.0 for Windows® Powerful new charts and graphs made easy Page 6 ■ SPSS Text Analysis for Surveys™ 2.0 Get more value from open responses Page 10 ■ SPSS 13.0 for Mac® OS X Major advances in access and data management Page 12 ■ SPSS Advanced Models™ 15.0 Address more statistical modeling problems Page 16 ■ Amos™ 7.0 Amos makes Structural Equation Modeling easy Page 42 ■ And much more! Inside The marriage of love and analytics: How eHarmony uses SPSS software to bring happiness to millions. SPSS Product Catalog Your complete data analysis sourcebook Page 2 Volume 10 ■ 2006 Cover Story R ecently, eHarmony, the online dating giant, began extensive use of SPSS predictive analytical software for scientific research, brand development, compatibility models, customer satisfaction and retention, and product research. eHarmony wants to make sure its researchers and psychologists harness the full power of predictive analytics for the organization and its customers. Mining For Love In Myriad Places By Rick Whiting Reprinted with permission from InformationWeek C an predictive analysis be used to find true love? Researchers at eHarmony have begun using such tools to build the algorithmic models that power the online matchmaker’s relationship services. “SPSS is the lens through which we view our data. The numerous analytic and data management tools it provides have enabled our organization to understand important information in more novel, forward-thinking ways.” – Steve Carter, eHarmony Senior Director of Research and Development 2 1.800.253.2575 (U.S. only) Order now! When dating site eHarmony got its start in 2000, it hired social psychologists who interviewed married couples to figure out which characteristics—values, interests, personality traits—make for a successful relationship. Today the company has more than 11 million registered users and claims that, on average, more than 90 eHarmony members marry every day after being matched on its site. (No mention of how many matches end in divorce.) The cyber-Cupid is shooting for higher success rates. That means identifying more variables to add to the operational models and more effectively measuring the variables it already has. “There have to be tons of things we haven’t identified yet,” says Steve Carter, eHarmony’s senior director of research and development. The software, from SPSS, will be used by eHarmony for scientific research, brand development, compatibility models, customer satisfaction and retention, and product research. One plan: Begin tracking couples before they get married to figure out which relationships last and which ones don’t. The company should think about sharing those significant findings with the rest of the world. www.spss.com Table of Contents Featuring 6 Software Showcase SPSS 15.0 for Windows 10 Analyze data using comprehensive statistical software SPSS Text Analysis for Surveys 2.0 12 NEW version SPSS 13.0 for Mac OS X Comprehensive statistical software for your Mac Complement SPSS with these products to form a complete analytical system Updated 32 SPSS Missing Value Analysis™ 15.0 SPSS Categories™ 15.0 34 SPSS Regression Models™ 15.0 22 SPSS Classification Trees™ 15.0 36 SPSS Tables™ 15.0 24 SPSS Complex Samples 15.0 38 SPSS Trends™ 15.0 16 SPSS Advanced Models™ 15.0 20 28 30 31 Enter the realm of powerful and sophisticated analyses Unleash the full potential of your multivariate data analysis Uncover patterns in your data with powerful tree-growing algorithms ™ Updated Correctly and easily compute statistics for complex samples 40 SPSS Conjoint™ 15.0 Discover what drives your customers’ purchase decisions SPSS Data Preparation™ 15.0 Improve data preparation for more accurate results SPSS Exact Tests™ 15.0 Reach accurate conclusions with small samples or rare occurrences SPSS Maps™ 15.0 Updated Create higher-value data and build better models when you estimate missing data Updated Make better predictions with powerful regression procedures Build expert time-series forecasts— in a flash SPSS Server 15.0 Updated Maximize productivity with SPSS Server 2 Cover Story 5 SPSS in the News 14 The Analytical Process 54 SPSS Tip NEW version 42 Amos™ 7.0 44 Answer Tree® 3.1 46 SPSS Data Entry ™ 4.0 48 SamplePower ® 2.0 51 SPSS SmartViewer ® Web Server ™ 5.0 Create custom tables in no time Editorial Departments Chart a course for better decision making www.spss.com All-new version! SPSS Stand-alone Products SPSS Family Expand your analytical capabilities with SPSS add-on modules 26 Updated Enhance the analytical value of text responses Expanded statistical options based on Bayesian estimation Target the right people more effectively using intuitive decision trees Your complete system for collecting and managing survey research data Save time, effort, and money by identifying the sample size you need Deploy SPSS results with interactive Web reporting 52 Clementine® Desktop™ 53 mrInterview ™ 3.5 and mrTables™ 3.5 Quickly add the power of data mining to your analysis Create and conduct surveys with confidence Mining For Love In Myriad Places Icon Key Noteworthy headlines and articles SPSS end-to-end story SPSS Module Training is available www.spss.com/training SPSS add-on module Clean up datasets with the REPLACE function 1.800.253.2575 (U.S. only) Order now! 3 Would you buy a high-performance vehicle and never take it out of first gear? Then consider SPSS training to maximize your software investment. Your purchase of SPSS software means you’ve bought SPSS training offers: a sophisticated analytical tool that has real depth and ■ power. Wouldn’t you like to be up to speed quickly on all the ways your purchase can make your life easier 60+ public courses, available at more than 20 locations throughout North America ■ and your organization more profitable? Private training fully customized to your business or organizational needs ■ On-site training at your location That’s why SPSS offers training for almost every ■ One-to-one, in-person training software product and various applications. We ■ Live instruction via the Web for individuals provide a full range of opportunities to get the quality instruction you require. Whether you prefer classroom interaction or the convenience of learning via the Web, you’ll find a format to fit your needs. and groups ■ Web-Based Training for on-demand learning For more information, check your SPSS Training Catalog or visit www.spss.com/training. Get course descriptions, dates, times, and locations of your preferred courses, plus money-saving training discounts. Or call an SPSS representative at 1.800.543.5815. SPSS In the News Noteworthy headlines and articles West Point, Army Select SPSS to Predict Success Factors and Identify Trends T he United States Military Academy at West Point (USMA) has selected SPSS software to determine the success of cadets at the academy and as career officers. “We’ve selected SPSS as our assessment tool to help us achieve our overriding mission—to produce the highest quality career officers. With SPSS, we’ll better answer age-old questions with forwardlooking technology,” said West Point’s Institutional Research and Analysis Branch Chief Lt. Col. Michael J. Johnson. To effectively evaluate cadets’ performance, West Point will build models with more than 20 years of personal characteristics collected from institutional survey data. Those characteristics will be used to determine the best predictors of success as a cadet and as an Army officer. SPSS is also used by the U.S. Army Combat Readiness Center (CRC) to identify trends within risk-related data, improving the Center’s ability to predict, control, and prevent hazards threatening U.S. troops. Additionally, the U.S. Army’s Critical Infrastructure Assurance Program for Cyber Threats (CIAP-CT) deploys SPSS to identify and correlate cyberrelated attack patterns that threaten critical infrastructures. SPSS Named As Leader in Customer Data Mining by Leading Industry Analyst Firm Gartner, Inc. has positioned SPSS as one of two company leaders in the business marketplace for customer data mining. According to Gartner, Leaders are performing well today, have a clear vision of market direction, and are actively building competencies to sustain their leadership position in the market. “We’re deeply honored to be positioned by Gartner in the Leaders’ Quadrant for customer data mining,” said SPSS President and CEO Jack Noonan. “We believe this is a very significant, independent confirmation of our technological market position and success. As our predictive analytics software is driving high ROI with leading organizations worldwide, SPSS continues to receive recognition from top industry experts.” Last year, SPSS was selected by CRMGuru.com as the most customer-centric solution provider in marketing automation. CRMGuru.com is the world’s largest industry portal for business executives to learn about Customer Relationship Management (CRM). SPSS Software Helping to “Mushroom” Business for International Produce Company SPSS software is enabling Monterey Mushrooms Inc. to more effectively run all facets of its business from its facilities in the United States, Canada, and Mexico. Monterey Mushrooms is the largest grower/shipper and marketer of fresh mushrooms in the United States. SPSS software is used in many areas of the business, including sales reporting, payroll balancing, freight distribution, human resources, and asset management/general ledger reporting. See “Mushroom,” continued on page 55 www.spss.com 1.800.253.2575 (U.S. only) Order now! 5 SPSS 15.0 for Windows ■ ■ ■ Save time with easy data access and management Get a broad range of statistics for better analysis Report results in an easy-to-understand format NEW version “The feature set of 15.0 is irresistible. SPSS 15.0 offers a great set of new features that help convert an unwieldy dataset into usable information. It also improves my ability to communicate my analyses and results to consumers who are informed, but non-technical.” – Victor Kogler, Consultant, Contra Costa Health Services Server available See page 40 Analyze data using comprehensive statistical software SPSS for Windows, the premier statistical software product for data analysis and data management, helps solve your business and research problems. SPSS for Windows is a modular, tightly integrated, full-featured product line that allows you to add modules and products to ensure you meet all your analytical needs. SPSS for Windows, unlike other data analysis packages, is easier to use, has a correspondingly lower total cost of ownership, and comprehensively addresses the entire analytical process. Underlying this offering are more than 35 years of SPSS analytical expertise, assuring users that the included statistics and procedures are tried, tested, and proven as among the best in the field. Prepare your data in a flash Clustering technique handles large datasets Now you are ready to prepare your data for analysis—with SPSS 15.0 you can do this more quickly and easily. Eliminate the timeconsuming task of labeling all your data. Create your labels once and the Define Variable Properties tool copies and presents your labels to your entire dataset. The Identify Duplicate Cases tool and the Restructure Data Wizard help make sure your data is clear and organized properly for analysis. Get the most accurate identification of clusters in your data with the TwoStep Cluster procedure in SPSS 15.0. This state-of-the-art algorithm will allow you to find clusters in large and mixed datasets with continuous and categorical level variables. Prepare continuous-level data for analysis The Visual Bander allows you to easily create bands (such as breaking income into bands of $10,000 or ages into demographic groups). A data pass creates a histogram that enables you to interactively create cutpoints and automatically create data value labels for them. Save time with easy data access Begin your analysis by quickly accessing massive amounts of data from numerous database sources with SPSS 15.0’s Database Wizard—without having to write code or syntax. The Database Wizard guides you through the process of accessing data and generates code in the background. Plus, with the right drivers, you can connect to any ODBC-compliant database—resulting in minimal data handling using conversion-free/ copy-free data access. You’ll save time because you won’t have to convert data into SPSS format. SPSS 15.0 also empowers you by giving you easy access to SAS®, Excel®, and text data. 6 1.800.253.2575 (U.S. only) Order now! Powerful statistics for better analysis Start generating decision-making information quickly using powerful statistics. SPSS 15.0 empowers you with a broad range of statistics so you can get the most accurate response for specific data types. SPSS 15.0’s statistical lineup includes an extensive variety of procedures for descriptive analysis, numerical prediction, group identification, and forecasting. Present your best results with report OLAP SPSS 15.0’s report OLAP (Online Analytical Processing) features give you a fast, flexible way to create, distribute, and manipulate information for ad-hoc decision making. Create frequency tables, graphs, and report cubes that feature SPSS’ unique, award-winning pivoting technology. And create comparisons between past and present data—down to the percent— with the percent change in OLAP cube feature. Export your results to a variety of programs SPSS 15.0 makes it easy to integrate your SPSS output into your reports by enabling you to automatically export results into Microsoft® Word, Excel, PowerPoint®, and as a PDF document. Plus, you can export your data into Excel and SAS. Get increased flexibility when you add SPSS 15.0 modules to your SPSS Base system. Expand your analytical capabilities to fit any stage in the analytical process. For more details and complete specifications, go to www.spss.com/spss Stages for seamless statistical analysis 1 Save time with easy data access 2 What’s New in SPSS 15.0 for Windows Get to the analysis stage faster Enhance your reporting capabilities ■ ■ ■ Create your favorite charts instantly with an expanded Chart Builder Use dual-Y axis and overlay charts for more complex analysis Easily export SPSS reports as PDF documents More powerful data management ■ ■ ■ Quickly access massive amounts of data from numerous database sources with SPSS’ Database Wizard. SPSS gives you direct access to Excel, SAS, and text data. You will never have to waste time re-keying data for analysis. 3 Continuous-level data made easy with the Visual Bander 4 For continuous-level data, the Visual Bander lets you easily create bands (e.g., breaking ages or income into specific ranges). A data pass provides you with a histogram that helps you specify logical cutpoints. 5 Eliminate the time-consuming task of labeling all your data with the Define Variables Properties tool. Create your labels once, and the Define Variable Properties tool copies and presents your labels to your entire dataset. Present your best results with report OLAP Create, distribute, and manipulate information for adhoc decision making—featuring SPSS’ award-wining pivoting technology. Get a broad range of statistics for your analysis Get a wealth of statistical techniques—from data displays to prediction—so you can choose the most accurate procedure to solve your business and research problems. 6 Expanded programmability functionality ■ ■ ■ ■ Use plug-ins for Python® or the .NET version of Microsoft Visual Basic® to create applications Gain access to the SPSS backend through an open extension to write code using Python, and include it within SPSS production syntax jobs Add user-defined procedures to SPSS, provide a user interface, and send results from these procedures into an SPSS pivot table in the Output Viewer Updated SPSS Advanced Models — two new popular statistics Updated SPSS Complex Samples — ordinal regression and SRS estimators Updated SPSS Data Preparation — new optimal binning options Select from three types of optimal binning for preprocessing data prior to model building: Unsupervised, supervised, and hybrid approach Report your results in a format everyone can access Export your SPSS results directly into Microsoft Word and Microsoft Excel. Plus, you can export your SPSS data into Excel or SAS, or as a PDF document. 8.59% 19.53% 16.02% 17.58% For more details and complete specifications, go to www.spss.com/spss Easily write back to databases form SPSS by using the Export to Database Wizard Create your own dictionary information for variables with Custom Attributes Work more easily with very wide data files by using customized Variable Sets 38.28% 1.800.253.2575 (U.S. only) Order now! 7 Continued from page 7 New features and SPSS 15.0 for Windows Enhanced reporting capabilities Use the Chart Builder to create a variety of commonly used charts, such as box plots (shown here), histograms, and scatterplot matrices, with ease. This highly visual chart creation interface enables you to create a chart by dragging variables and elements onto a chart creation canvas. Expand your chart-making capabilities with Chart Builder. In a just a few clicks, you can create popular chart types with this highly visual chart creation interface. This intuitive, powerful interface will help you to save time and expand your chart creation capabilities. Enhance your graphs with these new features available in Chart Builder: New chart types: Box plot, high-low, histogram, and more 3-D bar charts displaying simultaneous clustering and stacking In SPSS 15.0, you can create an overlay chart with two independent Y axes based on different scales. This chart shows appraised land value and appraised value of improvements plotted against sale price—all in one frame. Paneling and summaries of separate variables Line charts displaying error bars and variables on drop lines Error bars on bar and area charts New chart types: Dual-Y axis and overlay charts. These charts will enable more complex analysis, reveal complex information, and allow for more sophisticated reporting. Export SPSS reports as PDF documents, making it even easier to share results with others. Export SPSS reports as PDF documents. SPSS 15.0 makes it even easier to share results with others. Product specifications Symbol indicates a new feature. Data access and data export ■ Open multiple data files simultaneously in a single SPSS session ■ Stata data file import/export ■ Dimension data model, enabling you to import/export data to/from Dimensions products ■ Ability to import from and export to OLE DB data sources without having to go through ODBC ■ Database Wizard ■ Import SAS data ■ Text Wizard ■ Import/export Excel data ■ Easily write back to databases from SPSS by using the Database Wizard. For example, you can: – Create a new table and export it 8 to your database – Add new rows to an existing table – Add new columns to an existing table – Export data to existing columns in a table ■ Save comma-separated value (CSV) text files from SPSS data files ■ Export output to PowerPoint, Word, and Excel Data management and preparation ■ Prepare continuous-level data for analysis with the Visual Bander ■ Create your own custom programs with the Output Management System. Turn output from SPSS procedures into data and create your own programs for: Bootstrapping; Jackknifing and Leaving One Out methods; and Monte Carlo simulations – Create custom routines in SPSS with the OMS Control Panel 1.800.253.2575 (U.S. only) Order now! ■ ■ ■ ■ ■ ■ ■ ■ ■ ■ ■ Easily clean your data when you identify duplicate records with the Identify Duplicate Cases tool Make sense and keep track of your data files by adding notes to them with the Data File Comments command Create read-only datasets More accurately describe your data using longer variable names (up to 64 bytes) Create value labels up to 120 characters (double that of previous versions) Clone or duplicate datasets Apply an extended Variable Properties command to customize properties for individual users Longer text stings (up to 32,000 bytes) Define Variables Properties tool Copy Data Properties tool Data Restructure Wizard ■ ■ ■ ■ Aggregate data to external or to the active data file Automatically convert string variables to numeric with Autorecode – Use an autorecode template to append existing recode schemes – Recode a set of variables that has a single scheme at one time – Autorecode blank strings so they are defined as “user-missing” Date and Time Wizard: – Easily work with data containing time and dates in SPSS – Create a time/date variable from a string containing a date variable – Create a time/date variable from variables that include individual date units, such as month or year – Calculate times and dates – Separate a date unit from a time/ date variable Apply splitters in the Data Editor for easier viewing of wide or long data files Create your own dictionary information for variables by using Custom Attributes. For example, create a custom attribute describing transformations for a derived variable with information explaining how it was transformed. ■ Customize the viewing of extremely wide files with Variable Sets. You can instantly reduce the variables shown in the Variable View and Data View windows to a subset while keeping the entire file loaded and available for analysis. Transformations ■ Easily find and replace text strings in your data using the find/replace function ■ Recode string or numeric value ■ Recode values into consecutive integers ■ Create conditional transformations ■ using DO IF, ELSE IF, ELSE, and END IF statements ■ Use programming structures, such as do repeat-end repeat, loop-end loop, and vectors ■ Compute new variables using arithmetic, cross-case, date and time, logical, missing-value, random-number, statistical, or string functions ■ Count occurrences of values across variables ■ Make transformations permanent or temporary ■ Execute transformations immediately, batched or on demand Descriptive statistics ■ Crosstabulations ■ Frequencies; Descriptives; Explore; Descriptive ratio statistics Bivariate statistics ■ Means; t tests; ANOVA; Correlation (Bivariate, Partial, Distances); and For more details and complete specifications, go to www.spss.com/spss capabilities in SPSS 15.0 for Windows More powerful data management Expanded programmability functionality helps make SPSS for Windows one Easily write back to databases from SPSS by using the Export to Database Wizard in the interface— previously possible only through syntax “SPSS 15.0 represents a valuable and important upgrade to an excellent tool, particularly for survey researchers because of the data management and manipulation features.” of the most powerful statistical development platforms. In SPSS 15.0, you can: Use plug-ins for Python® or the .NET version of Microsoft® Visual Basic® to create applications Create your own dictionary information for variables with Custom Attributes. For example, create custom attributes by including information explaining how you transformed existing variables. Gain access to the SPSS backend through an open extension. This enables you to write code using Python and include it within SPSS production syntax jobs. Work more easily with very wide data files by using customized variable sets. Instantly reduce the variables viewed in the Variable View and Data View windows, while keeping the entire file available for analysis. – King Douglas, Senior Analyst, American Airlines Introduce additional analytic functionality to SPSS. Add user-defined procedures to SPSS, provide an interface, and send result from these procedures into an SPSS pivot table in the Output Viewer. * Previously in SPSS Advanced Models Non-parametric tests Prediction for numerical outcomes and identifying groups ■ Factor Analysis ■ K-means Cluster Analysis ■ Hierarchical Cluster Analysis ■ TwoStep Cluster Analysis ■ Discriminant ■ Linear Regression ■ Ordinal regression—PLUM* Reporting ■ Reports – OLAP cubes – Case summaries – Report summaries Graphs ■ Categorical charts – 3-D Bar: Simple, cluster, and stacked – Bar: Simple, cluster, stacked, dropped shadow, and 3-D – Line: Simple, multiple, and drop-line – Area: Simple and stacked ■ ■ – Pie: Simple, exploding, and 3-D effect – High-low: High-low-close, difference area, and range bar – Box plot: Simple and clustered – Error bar: Simple and clustered – Error bars: Add to bar, line and area charts; and confidence level, S.D, or S.E. – Dual-Y axis and overlay Scatterplots – Simple, grouped, scatterplot matrix, and 3-D – Fit lines: Linear, quadratic, or cubic regression; Lowess smoother; confidence interval control; and for total or subgroups, display spikes to line – Bin points by color or marker size to prevent overlap Density charts – Population pyramids: Mirrored axis to compare distributions; with or without normal curve For more details and complete specifications, go to www.spss.com/spss ■ ■ ■ – Dot charts: Stacked dots show distribution; symmetric, stacked, and linear – Histograms: With or without normal curve; custom binning options Quality control charts – Pareto, X-Bar, range, Sigma, individual chart, or moving range chart – Automatic flagging of points that violate Shewhart rules, the ability to turn off rules, and the ability to suppress charts Diagnostic and exploratory charts – Caseplots and time-series plots – Probability plots – Autocorrelation and partial autocorrelation function plots – Cross-correlation function plots – Receiver-Operating Characteristics Multiple use charts – 2-D line charts (with 2 scale axes) – Charts for multiple response sets ■ ■ Custom charts – Graphics Production Language (GPL), a custom chart creation language, enables advanced users to attain a broader range of chart and option possibilities than the interface supports to create mixed charts and more Editing options – Automatically sort and reorder categories by label, value, or statistic – Data value labels: Drag and drop, add connecting lines, and match color to subgroup – Select and edit specific elements directly within a chart: Colors, text, and styles – Choose from a wide range of line styles and weights – Display gridlines, reference lines, legends, titles, footnotes, and annotations – Y=X reference line ■ ■ ■ Layout options – Paneled charts: Create a table of subcharts, one panel per level or condition; multiple row and columns – 3-D effects: Rotate, modify depth, and display backplanes Chart templates – Save selected characteristics of a chart and apply them to others automatically – Apply the following attributes at creation or edit time: Layout, titles, footnotes, and annotations; chart element styles; data element styles; axis scale range; axis scale settings; fit and reference lines; and scatterplot point binning – Tree-view layout and finer control of template bundles Export SPSS output to PDF – Choose to optimize the PDF for Web viewing – Control whether PDF-generated bookmarks correspond to Navigator Outline entries in the Output Viewer. Bookmarks facilitate navigation of large documents. – Control whether fonts are embedded in the document. Embedded fonts ensure that the reader of your document sees the text in its original font, preventing font substitution. ■ Easily open/save and create new output files through syntax System requirements ■ Operating system: Microsoft Windows XP or 2000 ® ■ Hardware: Intel Pentium®compatible processor ■ Memory: 256MB RAM minimum ■ Minimum free drive space: 400MB ■ SVGA monitor ■ Web browser: Internet Explorer 6 1.800.253.2575 (U.S. only) Order now! 9 Software Showcase SPSS Text Analysis for Surveys 2.0 ■ ■ ■ Gain greater analytical value from your text responses Save time by automating the creation of categories and the categorization of responses Save money by eliminating or reducing the need for outside coding services Easily make your survey text responses usable in quantitative analysis “Everything about the software saved me time, therefore saving the college money.” – Denyse Bening, Research Technician, Grand Rapids Community College 10 Updated SPSS Inc. created SPSS Text Analysis for Surveys to help you gain full value from text responses without the drudgery and expense associated with manual coding. Specifically designed for survey text, SPSS Text Analysis for Surveys is based on our automated LexiQuest™ natural language processing (NLP) software technologies. Using this software, you can automate the creation of categories and categorization of responses to transform unstructured survey data into quantitative data—without having to read text responses word-for-word. ■ ■ ■ When you use SPSS Text Analysis for Surveys, you are empowered to gain greater insight from text responses using these capabilities: ■ Dictionary-based text-extraction technology: This product ships with libraries and resources to automate concept extraction. You can easily customize these libraries by adding topic-specific terms to match your needs. 1.800.253.2575 (U.S. only) Order now! ■ Proven linguistic technologies: This product is based on SPSS Inc.’s LexiQuest™ natural language processing (NLP) technologies that enable you to quickly create categories and reliably categorize responses Visualization capabilities aid category refinement: Use bar charts, Web graphs, and Web tables to quickly reveal which categories contain co-occurring responses. Then decide whether to combine certain categories or to create new ones that better account for shared responses. Reuse and share categories: Save time and ensure reliability across the same or similar studies Export results to SPSS or Excel: Analyze and graph results in other software for use in decision making What’s New in SPSS Text Analysis for Surveys 2.0 New features and enhancements enable survey researchers to categorize text responses more quickly and reliably to support better quantitative analysis and business decisions. For instance, now you can: ■ ■ ■ ■ ■ Share project files with others for better collaboration Export categories for reuse by others in new projects Create conditional rules to categorize responses based on more complex information Profile categories using reference variables and bar charts Track coding progress by “flagging” responses For more details and complete specifications, go to www.spss.com/textanalysis_surveys Transform your open-ended text responses into easy-to-analyze data 1 Import survey text responses Import text responses from a variety of sources, including SPSS for Windows, Microsoft Excel, the SPSS Dimensions™ product family, and any ODBCcompliant database program. 4 2 3 Extract key concepts Extract key concepts automatically from responses to an open-ended question. The software creates a list of terms, types, and patterns. Simply click the “Extract” button (lower-left pane) to automatically extract concepts from the text responses. The single and multi-word concepts are color-coded to reveal their part of speech, such as red if negative. The Data pane shows the full text of all responses to the question. Refine categories Visualization capabilities enable you to quickly see which categories share responses. This can help you to refine categories manually. 5 Create categories and categorize text responses Automatically create categories and categorize responses using term derivation, term inclusion, a semantic network, or frequency. Also, categorize responses manually by dragging terms, types, and responses within the interface. Click the “Create Categories based on Linguistics” button at upper left to automatically create categories and categorize responses. Export results for analysis and graphing When you are satisfied with your categories, you can export results either as dichotomies or as categories. These can be used to create tables and graphs, either separately or in combination with other survey data. A Web graph showing which categories share responses enables the user to decide whether to combine certain categories or to create new ones that better account for shared responses. Results can also be exported to SPSS to create graphs that communicate survey findings. Export results to SPSS to create crosstabs or whatever your analysis requires. Product specifications Symbol indicates a new feature. Import data from: ■ SPSS (SAV), Dimensions (MDD), Excel (XLS), and ODBC-compliant databases Extract key concepts ■ Extract terms, types, and patterns automatically using linguistic resources ■ Supports manual review and refinement ■ Save extraction results Create categories ■ Supports the reuse of categories created in other programs ■ Use linguistic algorithms and a semantic network to automatically create categories and categorize responses ■ Create conditional rules to categorize responses by using extraction results and Boolean operators ■ Allows the “force-in” of an unextracted word or phrase into a category definition and automatically assigns responses containing it to that category ■ Allows the “force-in”/”force-out” of responses into/out of categories without changing the category definition Refine results ■ View response co-occurrence by using a category bar chart, Web graph, or Web table ■ Use “flags” to mark responses as completed or to follow-up ■ Profile categories by overlaying reference variables onto bar charts ■ Print category lists and some visualizations Export results (in the following file formats): ■ SPSS (SAV) and Excel (XLS) For more details and complete specifications, go to www.spss.com/textanalysis_surveys Share resources ■ Share project files that contain extracted results, categories, and linguistic resources ■ Export categories and definitions for reuse by others in new projects Dictionaries (customizable) ■ Type Dictionary: Supports the grouping of similar terms ■ Substitution Dictionary: Groups similar terms under a target name ■ Exclude Dictionary: Contains terms to be ignored during extraction Libraries ■ Survey Library: Contains resources related to pattern rules and ■ ■ ■ ■ types, as well as a predefined list of synonyms and excluded terms (proprietary) Project Library: Stores dictionary changes for a particular project Core Library: Contains reserved Type Dictionaries for Person, Location, Product, and Organization Budget Library: Contains a built-in type for words or phrases that represent qualifiers and adjectives Opinions Library: Contains seven built-in types that group terms for qualifiers and adjectives System requirements ■ Operating system: Microsoft Windows XP Professional, Service Pack 1 or higher; Windows 2000 Professional, Service Pack 4 ■ Hardware: – Processor: Intel® Pentium®-class; 3.0 GHz recommended – Monitor: 1024 x 768 (SVGA) res. – Memory: 256MB RAM minimum; 512MB recommended; 1GB or more for large datasets – Minimum free space: 300MB; more recommended for larger datasets 1.800.253.2575 (U.S. only) Order now! 11 Software Showcase SPSS 13.0 for Mac OS X also features two new add-on modules and updates to your favorite modules: SPSS 13.0 for Mac OS X ■ ■ ■ Analyze data with the most powerful statistical software for the Mac Access more reporting capabilities Save more time with easier data management NEW ■ ■ Comprehensive statistical software for your Mac ■ ■ ■ Symbol indicates a new feature. What’s New in SPSS 13.0 for Mac OS X SPSS 13.0 for Mac OS X provides a number of new features and capabilities to help you access and manage data, create graphics, and produce output. In addition, two new add-on modules—SPSS Classification Trees™ and SPSS Complex Samples™—enable you to more accurately work with certain data types. Enhancements to several other modules provide you with new 12 statistics and improve the way you create and present tables. SPSS 13.0 for Mac OS X enhancements Data and access management More powerful data management in SPSS 13.0 for Mac OS X provides you with a number of new features to save time, increase accuracy and reliability—and better manage your data. Graphics and output Enhanced reporting capabilities in SPSS 13.0 for Mac OS X enable you to produce professional-looking 1.800.253.2575 (U.S. only) Order now! graphs with ease, while the ability to export output to commonly used Microsoft Office applications gives you more options for communicating results. What’s New in SPSS 13.0 for Mac OS X: Add-on Modules SPSS 13.0 for Mac OS X is further enhanced by the addition of two new add-on modules and updates to several existing add-on modules. These new and enhanced modules are described to the right. SPSS Classification Trees 13.0 — Enables you to better identify groups, discover relationships between groups, and predict future events SPSS Complex Samples 13.0 — Provides the specialized planning tools and statistics you need when working with sample survey data Enhanced ■ Mac users can truly get excited about SPSS 13.0 for Mac OS X. It represents a significant upgrade from earlier versions—delivering major advances in access and data management, graphics creation, and output production. Product specifications NEW for time Mac OS X...it’s to get excited! New add-on module: SPSS Classification Trees SPSS Classification Trees enables you to better identify groups, discover relationships between groups, and predict future events. Create highly visual classification and decision trees that allow you to present categorical results in an intuitive manner—so you can more clearly explain categorical results to non-technical audiences. You can easily explore your results and visually determine how models flow. This can help you find specific subgroups and relationships that you might not uncover using more traditional statistics. SPSS Tables 13.0 — Preview tables as you build them with the new interactive table preview builder SPSS Regression Models 13.0 — Predict categorical outcomes with more than two categories with multinomial logistic regression (MLR) SPSS Categories 13.0 — Reveal underlying relationships between two or more nominal variables SPSS Advanced Models 13.0 — Expand on the GLM technique with the linear mixed models procedure and achieve more accurate models SPSS Classification Trees includes four established tree-growing algorithms: ■ CHAID ■ Exhaustive CHAID ■ Classification and regression trees (C&RT) ■ QUEST New add-on module: SPSS Complex Samples Do you analyze data from survey or market research, public health datasets, or government agencies? Do you use sample survey methodology in your research, or are your data likely to come from a public-use data set that includes complex sample designs? If you do, you need SPSS Complex Samples. Complex sample designs require specialized statistical techniques to account for the sample design and its associated standard errors. SPSS Complex Samples provides the specialized planning tools and statistics you need when working with sample survey data. It enables you to make more statistically valid inferences for a population by incorporating the sample design into survey analysis. Two algorithms— complex samples general linear For more details and complete specifications, go to www.spss.com/spss_mac Discover what’s new in SPSS 13.0 for Mac OS X SPSS 13.0 for Mac OS X features more powerful data management—giving you many new features to save time, and increase accuracy and reliability: ■ The new Visual Bander enables you to easily create bands (for example, break income into “bands” of 10,000 or break ages into groups). ■ The new Date and Time Wizard lets you calculate dates and times, such as calculating the length of time someone has been a patient. ■ Clean your data by identifying duplicate records through the user interface with the Identify Duplicate Cases tool. ■ More accurately describe your data by using longer variable names—expanded from eight bytes to 64 bytes. ■ Create your own custom programs with the output management system (OMS). model (GLM) and complex samples logistic regression—enable you to more accurately work with numerical and categorical outcomes in complex sample designs. Enhanced add-on module: SPSS Tables With SPSS Tables’ new interactive table preview builder, you can simplify the creation of custom tables by previewing tables as you build them. Simply drag your variables onto the table preview builder and make adjustments as necessary. Gain a high level of control over the layout and appearance of your tables by using category management features. Using the new Visual Bander, you can specify cutpoints in your data. Here, the user created interval cutpoints based on amount spent. Produce professional-looking graphs with ease using the enhanced reporting capabilities in SPSS 13.0 for Mac OS X. The new presentation graphics system makes it easy to create the graph you want and produce readable graph output: ■ Export output to commonly used Microsoft Office applications, expanding your options for communicating results. Export SPSS output to Excel, Word, and PowerPoint. ■ Choose from new chart types such as population pyramids, 3-D bar charts, error bar charts, and dot charts. ■ Further improve chart appearance by using additional chart display features and options, such as paneled charts, error bars on categorical charts, and data value labels that you can position anyplace on your chart. ■ Switch output language (e.g., switch between Japanese and English). For example, make your tables more precise by changing variable types or excluding categories. Additionally, use inferential statistics (or significance testing) in your tables to perform common analyses. SPSS Tables includes the following statistics: ■ Chi-square test of independence ■ Comparison of column means (t test) ■ Comparison of column proportions (z test) All of these enhancements make it easier for you to summarize and communicate even the most complicated results in a presentation-ready table format. For more details and complete specifications, go to www.spss.com/spss_mac Enhanced add-on module: SPSS Regression Models Easily find the best predictor from dozens of possible predictors by using the new stepwise function in multinomial logistic regression. Enhanced add-on module: SPSS Categories The new multiple correspondence analysis procedure in SPSS Categories greatly enhances this add-on module’s functionality. Use it to reveal the underlying relationships between two or more nominal variables when similar categories are grouped close to one another in a chart. New chart types make data reporting easier to read and understand. Here, the chart dynamically displays customers’ shopping styles. Enhanced add-on module: SPSS Advanced Models The linear mixed models procedure enables you to model means, variances, and covariances in your data. Several new techniques to help you create more accurate predictive models are now included in this procedure. For example, you can: ■ Select from 11 non-spatial covariance types, including first-order ante-dependence, heterogeneous, and first-order autoregressive ■ Save the standard error of prediction obtained from the procedure ■ Display the dependent variable’s estimated marginal means in cells and their standard errors for the specified factors by using the means subcommand for fixed effects Minimum system requirements Operating system: Mac OS X version 10.3.9 running Java™ 1.4.2 ■ Processor: G4 667MHz ■ Memory: 256MB RAM (512MB recommended for installations using Mac OS X Tiger™) ■ Monitor: Color monitor, 1024 x 768 resolution ■ Please note: SPSS does not support the use of any existing version of SPSS for Mac OS X on the new Intel®based Mac hardware. Some of the procedures result in incorrect numerical calculations under the Rosetta emulation software, rendering the results invalid. SPSS 13.0 for Mac OS X will prevent installation onto Intelbased hardware. The Intel-compatible version of SPSS for Mac OS X—SPSS 15.0 for Mac OS X—will be released in the second quarter of 2007. 1.800.253.2575 (U.S. only) Order now! 13 The Analytical Process SPSS products help you through each step Analytical projects can easily become a daunting task. So many steps and so little time—from planning and collection, all the way to getting the reports of your final analysis into the hands of the right people. SPSS’ integrated software—spanning the entire analytical process—will streamline your work. Since SPSS products work together, you won’t have to duplicate effort that might be required when using products from a variety of vendors. The analytical process is actually an iterative cycle. Once you’ve deployed your results, you use feedback about them to begin planning the next cycle. The diagram below outlines the steps and identifies SPSS products involved in each step of the analytical process. 1 2 3 Planning Data collection Data access Take the time to plan analytical projects at the beginning to reduce costs and wasted resources. Map a course of action instead of diving into analysis. SPSS has specially designed tools to help you estimate your sample size, launch more successful products, and more. Collect clean, unbiased, and up-to-date information in an efficient manner. SPSS gives you the tools to do this effectively, no matter how you’re collecting data. Quickly access massive amounts of data from numerous database sources by using the Database Wizard in SPSS. No longer do you need to write code or syntax— the Wizard guides you through the process of accessing data and generates code in the background. And, with the right drivers, you can connect to any ODBCcompliant database—resulting in minimal data handling using conversion-free/copy-free data access. You save time because you won’t have to convert data into the SPSS format. Products: SamplePower SPSS Complex Samples SPSS Conjoint Products: SPSS Data Entry mrInterview Product: SPSS for Windows Deployment Reporting Data analysis 14 7 1 Planning 2 Data collection 3 Data access 4 Data management and data preparation 6 5 1.800.253.2575 (U.S. only) Order now! www.spss.com/spss/analytical_process.htm 4 5 6 7 Data management and data preparation Prepare your data for analysis quickly with efficient data management and preparation. Products: SPSS for Windows SPSS Missing Value Analysis SPSS Data Preparation Data analysis Reporting Deployment The SPSS family of products offers a full range of statistics and techniques, including simple statistics, correlations and crosstabs, clustering techniques, and factor analysis, as well as predictive analysis, such as regression. SPSS gives you full support to perform the right statistical procedures for your data, based on what you want to learn and the level of measurement of the variables to help you maximize your analysis. Once your analysis is complete, you need to summarize results so nontechnical audiences can understand them. SPSS lets you easily condense and transform massive amounts of case data into readable, meaningful information, so you—and others—can better understand your customers, patients, or employees. Put your results in the hands of people who can use them to make a difference. SPSS makes it easy to securely share results with others—on the Web, in presentations, or in publications. Products: SPSS for Windows SPSS Regression Models SPSS Advanced Models SPSS Exact Tests SPSS Tables SPSS Complex Samples SPSS Categories SPSS Trends SPSS Classification Trees SPSS Text Analysis for Surveys Amos AnswerTree www.spss.com/spss/analytical_process.htm Product: SmartViewer Web Server Products: SPSS for Windows SPSS Classification Trees SPSS Tables SPSS Maps mrTables 1.800.253.2575 (U.S. only) Order now! 15 SPSS Advanced Models 15.0 ■ ■ ■ Require multiple outcomes Want to measure outcomes over time Analyze data with hierarchical structure Estimate length of time until an event Move beyond basic analysis Build flexible models using a wealth of model-building options Achieve more accurate predictive models using a wide range of modeling techniques Enter the realm of powerful and sophisticated analyses SPSS Module Updated Created to provide you with more statistical power, SPSS Advanced Models enables you to reach more accurate conclusions. Consider what it would be like to harness sophisticated univariate and multivariate analytical techniques and unleash them on your data. Break through the barrier between general analysis and advanced modeling, and begin reaping the rewards today. It’s time to step up your analysis when you… What’s new in SPSS Advanced Models 15.0 When you upgrade to SPSS Advanced Models 15.0, you get two new popular statistical procedures...generalized linear models (GZLMs) and generalized estimating equations (GEEs). Together they address a wide range of statistical modeling problems. GZLMs and GEEs represent a unifying framework that includes classical linear models with normally distributed dependent variable, logistic, and probit models for binary data, and loglinear models for count data, as well as various other nonstandard regression-type models. Specifically: ■ GZLMs cover not only widely used statistical models, such as linear regression for normally distributed responses, logistic models for binary data, and loglinear models for count data, but also many useful statistical models via its very general model formulation ■ GEEs extend generalized linear models to accommodate correlated longitudinal data and clustered data It’s a numbers game for Las Vegas casinos L as Vegas, the nation’s gaming mecca, is a constant draw for people who want to try their hand at lady luck. In fact, according to the 2005 AGA Survey of Casinos Entertainment, a record 54.1 million people visited casinos in 2004 nationwide. In the casino industry, it’s crucial for gaming organizations to carve a niche in the market. A large gaming organization needed answers to some very significant questions to prepare a market strategy. ■ What should the casino look like and what amenities should be featured? 16 1.800.253.2575 (U.S. only) Order now! ■ ■ ■ What factors (both gambling and adjunct activities) affect visitation? What type (profile) of people will the casino attract, to include travel distance? What is the “predictive” estimate of the planned casino users? To assist it in getting the answers to these questions, the organization hired principal statistician William Bailey from WMB & Associates. “This was a huge, complex project,” stated Bailey. So Bailey turned to SPSS for Windows and SPSS Advanced Models to help him to analyze the large amounts of complex data. “We created key drivers and factors to determine the viability of the project, and suggestions regarding activities, beyond gaming tables, that would encourage visiting the casino,” said Bailey. This offered guidance for his client to design the optimal floor plan and entertainment for the casino. Hundreds of pages of numbers and tables were generated from the data. Bailey and his team created 20-30 perceptual maps with SPSS. From this data they were able to make their findings more understandable for the client. “The client very favorably received our presentation, partly because SPSS allowed us to give them answers in an easy-tounderstand format. Even though this was such an enormous job, I knew SPSS for Windows with SPSS Advanced Models could easily handle the project,” said Bailey. “I have a tremendous amount of confidence in SPSS Advanced Models.” – William Bailey, Principal Statistician at WMB & Associates For more details and complete specifications, go to www.spss.com/advanced_models Comprehensive tools for today’s analyst SPSS Advanced Models meets the wide-range of statistical needs of today’s analyst. With its wealth of features and capabilities, you will never be limited to basic analytical techniques again. Along with what’s new, check out the powerful procedures you can choose from. General linear models (GLM) multivariate: Gain more flexibility to describe the relationship between a dependent variable and a set of independent variables. GLM doesn’t leave you limited to a single data type, but offers a wealth of model-building possibilities. Product specifications Achieve more accurate models A marketing group tests three campaigns to determine which promotion has the greatest effect on sales. 1 Identify random effects The marketing group specifies the fixed (promotion) and random effects (market ID) in a model to adjust for the covariance structure of the data. 2 Linear mixed models (Mixed): Expand on the GLM technique with the Mixed procedure and achieve more accurate models. Use the Mixed procedure to model means, variances, and covariances in your data when working with nested-structure data. Or use Mixed when working with repeated measures data, including situations in which there are different numbers of repeated measurements or different intervals for different cases, or both. Survival analysis: Analyze event history and duration data to better understand events. SPSS Advanced Models includes state-of-the-art survival procedures such as Kaplan-Meier and Cox Regression. Variance component estimation (VARCOMP): Choose from a number of methods to estimate the variance component for each random effect in a mixed model. Follow up your GLM analysis with variance component estimation analysis to estimate the variance. It’s easy to determine where to focus your attention when reducing the variance. 3 Symbol indicates a new feature. GZLMs and GEEs GZLMs procedures provide a unifying framework that includes classical linear models with normally distributed dependent variable, logistic, and probit models for binary data, and loglinear models for count data, as well as various other nonstandard regression-type models. GEEs procedures extend the generalized linear model to correlated longitudinal data and clustered data. Particularly, GEEs model correlations within subjects. ■ Provides a common framework for the following outcomes: continuous outcomes, count data, event/trial data, claim data, and correlated responses within subjects ■ Specify model effects, an offset or scale weight variable if either exists, the probability distribution, and the link function – Include or exclude the intercept – Specify an offset variable or fix the offset at a number – Specify a variable that contains Omega weight values for the scale parameter – Choose from probability distributions: Binomial, Gamma, inverse Gaussian, negative binomial, normal, and Poisson ■ – Choose link functions: Complementary loglog, identity, log, log complement, logit, negative binomial, negative log-log, odds power, probit, and power Control statistical criteria for generalized linear models and specify numerical tolerance for checking singularity. Specify: – Type of analysis for each model effect: Type I, Type III, or both – A value for starting iteration for checking complete and quasi-complete separation – The confidence interval level for coefficient estimates and estimated marginal means – Parameter estimate covariance matrix: Model-based estimator or robust estimator – Hessian convergence criterion – Initial values for parameter estimates – Log-likelihood convergence criterion – Form of the log-likelihood function – Maximum number of iterations for parameter estimation and log-likelihood – Maximum number of steps in step-halving method – Model parameters estimation method: Fisher scoring method or Newton-Raphson method Use the new GZLMs procedure Fit a wide variety of models for many types of outcomes with generalized linear models. For example, fit a Gamma regression for skewed outcomes, such as claim amounts. Loglinear analysis: Fit loglinear and logit models to count data so you can easily model and predict your outcomes. Analyze results using various methods The random effects variance is significant and larger than the residual variance. Most of the variability unaccounted for by the fixed effects is due to the market-to-market sales variation. For more details and complete specifications, go to www.spss.com/advanced_models 1.800.253.2575 (U.S. only) Order now! 17 Continued from page 17 Product specifications ■ ■ – Parameter convergence criterion – Method of fitting the scale parameter: Maximum likelihood, deviance, Pearson Chi-square, or fixed at a number – Tolerance value used to test for singularity Specify the working correlation matrix structure used by the GEE to model correlations within subjects, and control statistical criteria in the non-likelihood-based iterative fitting algorithm. Specify: – The within-subject or time effect – Correlation matrix structure: Independent working, AR(1) working, exchangeable working, fixed working, m-dependent working, and unstructured working – Whether to adjust the working correlation matrix estimator by the number of non-redundant parameters – Whether to use robust or the model-based estimator or parameter estimate covariance matrix for GEEs – The Hessian convergence criterion for the GEEs – Maximum iterations – Relative or absolute parameter convergence criterion – The number of iterations between updates of the working correlation matrix Display estimated marginal means of the dependent variable for all level combinations of a set of factors. Specify: – The cells for which estimated marginal means are displayed – The covariate values to use when computing the estimated marginal means – Whether to compute estimated marginal means based on the original scale of the dependent variable or on the link function transformation – The factor or set of crossed factors, the levels or level combinations which are compared using the contrast type specified – The type of contrast to use for the levels of the factor, or level combinations of the crossed factors. The following contrast types are available: Pairwise, deviation, difference, Helmert, polynomial, repeated, and simple. 18 – The method of adjusting the significance level used in tests of the contrasts: Least significant difference, Bonferroni, Sequential Bonferroni, Sidak, and Sequential ■ Display the following: Correlation matrix for parameter estimates, covariance matrix for parameter estimates, case processing summary, descriptive statistics, goodness of fit, general estimable function, iteration history, Lagrange multiplier test, set of contrast coefficient (L) matrices, model information, parameter estimates and corresponding statistics, model summary statistics, and working correlation matrix ■ Save to the working data file: Predicted value of the linear predictor, estimated standard error of the predicted value of the linear predictor, predicted value of the mean of the response, confidence interval for the mean of the response, leverage value, raw residual, Pearson residual, deviance residual, standardized Pearson residual, standardized deviance residual, likelihood residual, and Cook’s distance ■ Save to an external file: The parameter correlation matrix and other statistics to an SPSS dataset, the parameter covariance matrix and other statistics to an SPSS dataset, and the parameter estimates and the parameter covariance matrix to an XML file MIXED Expands the general linear model used in the GLM procedure so that data can exhibit correlation and non-constant variability ■ Fit the following types of models: – Fixed effects ANOVA model, randomized complete blocks design, split-plot design, purely random effects model, random coefficient model, multilevel analysis, unconditional linear growth model, linear growth model with person-level covariate, repeated measures analysis, and repeated measures analysis with timedependent covariate ■ Opt to apply frequency weights or regression weights ■ Use one of six covariance structures offered ■ Select from 11 non-spatial covariance types ■ Choose CRITERIA to control the iterative algorithm used in estimation 1.800.253.2575 (U.S. only) Order now! and to specify numerical tolerance for checking singularity ■ Specify the mixed model fixed effects: No intercept, Type I sum of squares, and Type III sum of squares ■ Specify the random effects: Identify the subjects and covariance structure (first-order autoregressive, compound symmetry, Huynh-Feldt, identity, and unstructured variance components) ■ Depending on the covariance type specified, random effects specified may be correlated ■ Estimation methods: Maximum likelihood and restricted maximum likelihood ■ Print covariance matrix of residual ■ Specify the residual covariance matrix in the mixed effects model ■ Save fixed predicted values, predicted values, and residuals ■ Customize hypotheses tests by specifying null hypotheses as linear combinations of parameters ■ Save standard error of prediction ■ Means subcommand for fixed effects, which displays the dependent variable’s estimated marginal means in the cells and its standard errors for the specified factors GLM Describe the relationship between a dependent variable and a set of independent variables ■ Select univariate and multivariate lack-of-fit tests ■ Regression model ■ Fixed effect ANOVA, ANCOVA, MANOVA, and MANCOVA ■ Random or mixed ANOVA and ANCOVA ■ Repeated measures: Univariate or multivariate ■ Doubly multivariate design ■ Four types of sums of squares ■ Full-parameterization approach to estimate parameters in the model ■ General linear hypothesis testing for parameters in the model ■ Write a covariance or correlation matrix of the parameter estimates in the model in a matrix data file ■ Plots: Spread vs. level, residual, and profile ■ Post hoc tests for observed cell means ■ Estimated population marginal means for predicted cell means ■ Save variables to the active file: Unstandardized predicted values, weighted unstandardized predicted values, unstandardized residuals, weighted unstandardized residuals, deleted residuals, standardized residuals, Studentized residuals, standard errors of predicted value, Cook’s distance, and uncentered leverage values ■ Pairwise comparisons of expected marginal means ■ Linear hypothesis testing of an effect vs. a linear combination of effects ■ Option to save design matrices ■ Contrasts: Deviations, simple, difference, Helmert, polynomial, repeated, and special ■ Print: Descriptive statistics, tests of homogeneity of variance, parameter estimates, partial Eta2, general estimable function table, lack-of-fit tests, observed power for each test, and a set of contrast coefficient (L) matrices VARCOMP Variance component estimation ■ Estimation methods: ANOVA MINQUE, maximum likelihood, and restricted maximum likelihood ■ Type I and Type III sums of squares for the ANOVA method ■ Choices of zero-weight or uniformweight methods ■ Choices of ML and REML calculation methods ■ Save variance components estimates and covariance matrices ■ Print: Expected mean squares, iteration history, and sums of squares LOGLINEAR (For a full description, see www.spss.com/advanced_models) HILOGLINEAR Hierarchical loglinear models for multiway contingency tables ■ Simultaneous entry and backward elimination methods ■ Print: Frequencies and residuals ■ Parameter estimates and partial associations for saturated models ■ Criteria specification: Convergence, maximum iterations, probability of Chi-square for model, and maximum steps ■ Specified cell weights and maximum order of terms ■ Plots of standardized residuals vs. observed and expected counts ■ Normal probability plots of standardized residuals GENLOG Fit loglinear and logit models to count data by means of a generalized linear model approach Model fit, using ML estimation under Poisson loglinear model and multinomial loglinear models ■ Accommodate structural zeros ■ Generalized log-odds ratio facility tests the specific generalized logodds ratios are equal to zero, and can print confidence intervals ■ Diagnostic plots: Scatterplots and normal probability plots of residuals ■ Criteria specification: Confidence interval, iterations, convergence, Delta, and Epsilon values used as tolerance in checking singularity SURVIVAL Analysis of life tables ■ Life tables for individual groups ■ Interval variable lengths ■ Plots: Cumulative survival distribution on log or linear scale, hazard function, and density function ■ Comparisons of subgroups ■ Plots of the one-minus survival function ■ Status variables to indicate if the terminal event occurred for the observation ■ Print life tables ■ Calculate comparisons of the subgroups: Exact, approximate, conditional, pairwise, and compare ■ Option to write survival table data records and label records files KAPLAN-MEIER Estimates the length of time to an event using Kaplan-Meier estimation methods ■ Define factors and strata ■ Plots: Cumulative hazard functions, cumulative, and log survival ■ Display censored cases ■ Save variables to a file: Cumulative number of events, hazard, standard error, and survival function ■ Statistical display: Cumulative events and survival, mean and median survival times with standard errors, number at risk, requested percentiles, and standard error ■ Tests for equality of survival distributions: Breslow, Tarone, and logrank ■ Specify a trend component for factor levels having a metric ■ Include plots of the one-minus survival function ■ Status variables to indicate if the terminal event occurred for the observation ■ Specify strata within categories of factors ■ Compare the survival distributions ■ for different levels of the factor: Compare all factor levels in a single test, compare each pair of factors, pool the test statistic across all strata, and compare the factor levels for each stratum COX REGRESSION Proportional hazards with timedependent covariates ■ Contrasts: Deviations, simple, difference, Helmert, polynomial, repeated, special, and indicator ■ Define strata to estimate separate baseline functions ■ Methods: Backward and forward stepwise and direct entry ■ Plots: Cumulative survival, hazard, and log-minus-log plots for each stratum ■ Removal of variables: Change in likelihood ratio, conditional, and Wald ■ Save variables to files: Baseline survival and hazard functions and their standard errors, cumulative hazard function, dfbeta, log-minuslog of survival function, residuals, and survival function ■ Plots of the one-minus survival function ■ Status variables to indicate if the terminal event occurred for the observation ■ Ordinal or nominal predictors ■ Print: Full regression output including overall model statistics for variables in the equation and variables not in the equation, summary information, correlation/covariance matrix of the parameter estimates for the variables in the model, baseline table, and confidence intervals for exponential of Beta ■ Criteria: Change in parameter estimates for terminating iteration; maximum number of iterations; percentage of change in log-likelihood ratio for terminating iteration; probability of score statistic for variable entry; and probability of Wald, likelihood ratio (LR), or conditional LR statistic to remove a variable ■ Specify the pattern of covariate values to be used for requested plots and coefficient tables ■ Write to external SPSS data files: Coefficients in the final model and survival table System requirements ■ SPSS 15.0 for Windows ■ Other system requirements vary according to platform For more details and complete specifications, go to www.spss.com/advanced_models Join us at the next See it in SPSS seminar and see the new ways SPSS can support your data analysis efforts. SEE IT IN See it in SPSS Agenda & Registration See it in SPSS is a free, half-day event for SPSS customers, featuring seminars highlighting the newest SPSS products, a complimentary networking lunch, and optional afternoon sessions. Check-in: 8:30 – 9:00 a.m. Introduction & Welcome 9:00 – 9:15 a.m. mrInterview 3.5 9:15 – 10:00 a.m. SPSS Text Analysis For Surveys 2.0 10:00 – 10:45 a.m. Break 10:45 – 11:00 a.m. Enhance SPSS with modules 11:00 – 11:30 a.m. SPSS 15.0 for Windows 11:30 a.m. – 12:15 p.m. Q&A 12:15 – 12:30 p.m. Complimentary networking lunch: 12:30 – 1:30 p.m. Optional afternoon sessions: Data Mining with Clementine 10.0 1:30 – 2:30 p.m. 2:30 – 3:30 p.m. (repeat) Discover how the newest version of Clementine offers you unbeatable productivity for data mining applications. Features include: ■ Better access to Dimensions survey data ■ New “anomaly detection” algorithm ■ New “feature selection” for CRM marketing applications Go to: www.spss.com/seeit for the schedule of upcoming cities. Announced cities include: New York, Chicago, Sacramento, Los Angeles, and Toronto End-to-end Survey Research Solutions 1:30 – 2:30 p.m. 2:30 – 3:30 p.m. (repeat) See how Dimensions helps you gain more value from customer interactions and improve your strategic planning and responsiveness to change. Rely on SPSS Categories whenever you need to: SPSS Categories 15.0 ■ ■ ■ SPSS Module Visualize how rows and columns of large tables of counts or means relate Visualize and explore multivariate categorical data Understand information in large two-way and multi-way tables See relationships in your data using revealing biplots and perceptual maps Determine how closely customers perceive your products to others in your offering set or your competitors’ Understand what characteristics consumers relate to most regarding product or brand Reveal underlying relationships through perceptual maps of categorical data Work with and understand ordinal and nominal data with procedures similar to conventional regression, principal components, and canonical correlation Perform regression analysis with a categorical dependent variable With SPSS Categories’ sophisticated procedures in your toolbox, you are no longer hampered by categorical or highly-dimensional data. These techniques ensure you have all the tools you need to easily analyze and interpret your multivariate data and its relationships more completely. Present your results clearly using perceptual maps Use dimension reduction techniques to go beyond unwieldy tables to clearly see relationships in your data using revealing perceptual maps and biplots. Summary charts display similar variables or categories, providing you with insight into relationships among more than two variables. The data are a 2x5x6 table containing information on two genders, five age groups, and six products. This plot shows the results of a two-dimensional multiple correspondence analysis of the table. Notice that products such as “A” and “B” are chosen at younger ages and by males, while products such as “G” and “C” are preferred at older ages. Product specifications PREFSCAL Multidimensional unfolding analysis ■ Read one or more rectangular matrices of proximities ■ Read weights, initial configurations, and fixed coordinates ■ Optionally transform proximities with linear, ordinal, smooth ordinal, or spline functions 20 ■ ■ ■ ■ Specify multidimensional unfolding with identity, weighted Euclidean, or generalized Euclidean models Specify fixed row and column coordinates to restrict the configuration Specify initial configuration (classical triangle, classical Spearman, Ross-Cliff, correspondence, centroids, random starts, or custom), iteration criteria, and penalty parameters Specify plots for multiple starts, 1.800.253.2575 (U.S. only) Order now! ■ initial common space, stress per dimension, final common space, space weights, individual spaces, scatterplot of fit, residuals plot, transformation plots, and Shepard plots Specify output that includes the input data, multiple starts, initial common space, iteration history, fit measures, stress decomposition, final common space, space weights, individual ■ spaces, fitted distances, and transformed proximities Write common space coordinates, individual weights, distances, and transformed proximities to a file PROXSCAL Statistics: Iteration history, stress measures, stress decomposition, coordinates of the common space, object distances within the final configuration, individual ■ ■ space weights, individual spaces, transformed proximities, and transformed independent variables Plots: Stress plots, common space scatterplots, individual space weight scatterplots, individual spaces scatterplots, transformation plots, Shepard residual plots, independent variables transformation plots, and correlations plots CATPCA Statistics: Frequencies, missing values, optimal scaling level, mode, variance accounted for by centroid coordinates, vector coordinates, total per variable and per dimension, component loadings for vector-quantified variables, category quantifications and coordinates, iteration history, correlations of the transformed variables and eigenvalues of the ■ For more details and complete specifications, go to www.spss.com/categories Unleash the full potential of your data through optimal scaling and dimension reduction techniques Correspondence analysis (CORRESPONDENCE): Describe the relationships between two nominal variables in a low-dimensional space, while simultaneously describing the relationships between categories for each variable. 1 Analyze differences between categories 2 Incorporate supplementary information Use correspondence analysis to easily display and analyze differences between categories. In this example, researchers present and analyze the two-dimension table relating staff group to smoking category in a particular workplace. Categorical regression (CATREG): Predict the values of a categorical dependent variable from a combination of categorical independent variables. Multiple correspondence analysis (MULTIPLE CORRESPONDENCE): Analyze a categorical multivariate data matrix when all the variables are analyzed at the nominal level. Similar to correspondence analysis except it doesn’t limit you to only two variables. Categorical Principal Components Analysis (CATPCA): Use alternating least squares to generalize principal components analysis to accommodate variables of mixed measurement levels. Specify a transformation type of nominal, ordinal, or numeric on a variable-byvariable basis. Nonlinear canonical correlation (OVERALS): Use alternating least squares to generalize canonical correlation analysis. It allows more than one set of variables to be compared to one another on the same graph. Proximity scaling (PROXSCAL): Takes a matrix of similarity and dissimilarity distances between observations in a high-dimensional space and assigns them to a position in a low-dimensional space in order for you to gain “spatial” understanding of how objects relate. 3 Uncover associations and relationships Using symmetrical normalization to produce a biplot, the researchers conclude that a strong association does not exist in the sample between non-drinking and nonsmoking, and there is a suggested association between drinking and level of smoking with relatively more drinkers in the high-smoking group. Easily incorporate supplementary information on additional variables in SPSS Categories. Here, additional information on alcohol consumption by staff group is known. These additional columns can be projected into the staff group by smoking category space. Preference scaling (PREFSCAL): Set up the Preference Scaling procedure (PREFSCAL) in syntax to perform multidimensional unfolding on two sets of objects in order to find a common quantitative scale. ■ correlation matrix, correlations of the original variables and eigenvalues of the correlation matrix, and object scores Plots: Joint category plots, transformation plots, residual plots, projected centroid plots, object plots, biplots, triplots, and component loadings plots CORRESPONDENCE ■ Statistics: Correspondence measures; row and column profiles; singular values; row and column scores; inertia, mass, row, and column score confidence statistics; and singular value confidence statistics ■ Plots: Transformation plots, row point plots, column point plots, and biplots CATREG ■ Statistics: Frequencies, regression coefficients, ANOVA table, iteration ■ history, and category quantifications Plots: Correlations between untransformed predictors, correlations between transformed predictors, residual plots, and transformation plots MULTIPLE CORRESPONDENCE ■ Statistics: Model summary; history statistics, descriptive statistics; discrimination measures; category quantifications; inertia of the For more details and complete specifications, go to www.spss.com/categories ■ categories; contribution of the categories to the inertia of the dimensions and contribution of the dimensions to the inertia of the categories; iteration history, correlations of the transformed variables, and the eigenvalues of this correlation matrix; correlations of the original variables and the eigenvalues of this correlation matrix; and object scores Plots: Object points, category points (centroid coordinates), discrimination measures, transformation (optimal category quantifications against category indicators), residuals per variable, objects and variables (centroids), and joint plot of the category points for the variables in the varlist OVERALS ■ Statistics: Frequencies, centroids, iteration history, object scores, ■ category quantifications, weights, component loadings, and single and multiple fit Plots: Object scores plots, category coordinates plots, component loadings plots, category centroids plots, and transformation plots System requirements SPSS 15.0 for Windows ■ 1.800.253.2575 (U.S. only) Order now! 21 UNICEF increased direct mail response by up to 80 percent SPSS Classification Trees 15.0 ■ ■ ■ SPSS Module Create classification trees directly within SPSS 15.0 for Windows Identify patterns, segments, and groups in your data Choose from four established tree-growing algorithms W ith more than 1 million donors, UNICEF Germany finances its projects to help children in less-developed countries through fundraising in the form of donations and sales of greeting cards. Create classification trees for better identification of groups directly within SPSS for Windows Faced with an increasingly tight budget and a continuously growing number of competitors, UNICEF Germany turned to Ogilvy & Mather Dataconsult (O&MDC) to better segment its target donors. “The goal was to uncover particular donor characteristics to maximize returns,” said Matthias SingerFischer, Senior Consultant, Ogilvy and Mather Dataconsult. The SPSS Classification Trees add-on module creates classification and decision trees directly within SPSS to identify groups, discover relationships, and predict future events. By creating visual trees, you are able to present results in an intuitive manner—so you can more clearly explain results to non-technical audiences. Using five years of historical data from the UNICEF database, O&MDC gathered approximately 30 variables, including standard demographics, donation frequency, date of last donation, sum of all recent donations, and several variables specific to UNICEF, such as preferred causes. Why SPSS Classification Trees should be added to your SPSS desktop: Access directly within SPSS for Windows—you never leave the SPSS environment Identify groups, segments, and patterns in a highly visual manner with classification trees Because of the host of variables and different scale levels, O&MDC used a Chi-square-based (CHAID) segmentation method. The CHAID procedure is currently one of four powerful decision-tree algorithms in SPSS Classification Trees. Present results in an intuitive manner— perfect for non-technical audiences Save information from trees as new variables in data (information such as terminal node number, predicted value, and predicted probabilities) The results gave UNICEF Germany a clearer understanding of its donors. Consequently, UNICEF Germany was able to: ■ Increase direct mail response rate up to 80 percent ■ Raise the return on investment more than 65 percent ■ Target donors who are partial to the featured topic, thus ensuring a better distribution among UNICEF donors ■ Decrease mailing volume dramatically without affecting revenue from donations Choose from CHAID, Exhaustive CHAID, C&RT, and QUEST to find the best fit for your data Product specifications ■ Key features ■ Create tree-based classification models for: – Segmentation – Stratification – Prediction – Data reduction and variable screening – Interaction identification 22 ■ ■ – Category merging and discretizing continuous variables Classify cases into groups or predict values of a dependent (target) variable based on values of independent (predictor) variables Validation tools for exploratory and confirmatory classification analysis View nodes using one of several ways: Show bar charts of your target variables, tables, or both in each node 1.800.253.2575 (U.S. only) Order now! Collapse and expand branches without deleting the model ■ Generate syntax automatically from the UI ■ Re-run tree building using syntax in production mode ■ Score data based on results or use results in further analysis using other SPSS procedures Algorithms ■ Four powerful tree modeling algorithms: ■ – CHAID by Kass (1980) – Exhaustive CHAID by Biggs, de Ville and Suen (1991) – Classification & Regression Trees (C&RT) by Breiman, Friedman, Olshen and Stone (1984) – QUEST by Loh and Shih (1997) Evaluation ■ Evaluation graphs enable visual representation of gains summary tables ■ Misclassification functionality Gains chart: Identify segments by highest (and lowest) contribution Deployment ■ Export output objects to any of SPSS’ available output formats ■ Generate rules that define selected segments in SQL to score databases or SPSS syntax to score SPSS files ■ Export XML models to score cases using the scoring engine feature in SPSS Server (version 13.0 and higher) ■ Get native access to database management systems including Oracle, SQL Server, DB2; additional access to any ODBC-compliant sources using the ODBC Wizard System requirements ■ SPSS 15.0 for Windows ■ For more details and complete specifications, go to www.spss.com/classification_trees Uncover patterns in your data with powerful tree-growing algorithms The four algorithms in this add-on module differ from more traditional statistics, such as logistic regression, because these algorithms produce trees that enable you to explore your results and visually determine how your model flows. SPSS Classification Trees makes it easier to identify specific subgroups and relationships in your data than if more traditional statistics were used. It breaks your data into branches and nodes, so you can easily see where a group splits and terminates. SPSS Classification Trees includes four established tree-growing algorithms. Find the best fit for your data by trying different algorithms or let SPSS Classification Trees suggest the most appropriate algorithm. ■ CHAID — A statistical multi-way tree algorithm that explores data quickly and builds segments and profiles with respect to the desired outcome ■ Exhaustive CHAID — A modification of CHAID that examines all possible splits for each predictor (independent) variable ■ Classification & Regression Trees (C&RT) — A complete binary tree algorithm, which partitions data and produces accurate homogeneous subsets ■ QUEST — A statistical algorithm that selects variables without bias and builds accurate binary trees quickly and efficiently 1 Find the best fit for your data 2 Use highly visual trees to discover relationships in your data Choose from the following algorithms: CHAID, Exhaustive CHAID, C&RT, and QUEST in SPSS. 3 Apply results to your data Once you have produced your classification tree(s), you can dig deeper into your data and gain more insight by identifying a particular subset of the data via the tree, and then run further analysis on this group. SPSS Classification Trees makes it easy to interpret results with diagrams, tables, and graphs. By producing classification trees, you can discover relationships that are currently hidden in your data and add annotations for more detailed descriptions. Segment and group cases directly within the data Since you are creating classification trees directly within SPSS, you can use the results to segment and group cases directly within the data—without ever leaving the SPSS environment. Additionally, you can generate selection or classification/prediction rules in the form of SPSS syntax, SQL statements, or simple text. Display these rules in the Viewer and save them to an external file for later use to make predictions about individual and new cases. Directly select cases or assign predictions in SPSS based on the model results, or export rules for later use. Score cases directly in SPSS using the tree model results. For more details and complete specifications, go to www.spss.com/classification_trees 1.800.253.2575 (U.S. only) Order now! 23 Get a clearer view of what your data holds with complex sampling SPSS Complex Samples 15.0 ■ ■ ■ Achieve more statistically valid inferences for populations Get more accurate results from your survey data Analyze data and interpret results easily A marketing manager wants to know whether big-ticket customers (organizations that spend more than $100,000) are more satisfied than smaller-value customers. To uncover this information, it was decided to survey the customer database and build a model to predict customer satisfaction. But to implement a survey to the entire database would not be cost effective. Instead, 1,000 customers were chosen to be the sample of the population. Updated Correctly and easily compute statistics for complex samples SPSS Module If a simple random sample of 1,000 customers was pulled, not enough big-ticket customers would be provided to build a reliable model, as big-ticket customers tend to be rare. Due to the variability of characteristics, it is necessary to apply scientific sample designs in the sample selection process to reduce the risk of a distorted view of the population. If you’re working with complex sample designs, such as stratified, clustered, or multistage sampling, you need specialized statistical techniques to account for the sample design and its associated standard error. The SPSS Complex Samples add-on module for SPSS for Windows gives you everything you need for working with complex samples—from the planning stage and sampling through to the analysis stage. To build an accurate predictive model for the complex sample, the manager used SPSS Complex Samples. It was necessary to stratify the customers into big-ticket and smaller-value customer groups. The manager then drew a random sample of 500 within each of these groups to conduct the survey. SPSS Complex Samples helps you: Get a more accurate picture of your data when working with large-scale surveys Achieve more statistically valid inferences for populations Reach correct point estimates for statistics such as totals, means, and ratios, and obtain standard errors of these statistics Predict numerical and categorical outcomes from non-simple random samples Take up to three stages into account when analyzing data from a multistage design Product specifications Symbol indicates a new feature. Complex Samples Plan (CSPLAN) Provides a common place to specify the sampling frame to create a complex sample design or analysis design used by procedures in SPSS Complex Samples. To sample cases, use a sample design created by CSPLAN as input to the CSSELECT procedure. To analyze sample data, use an analysis design created by CSPLAN as input to the CSDESCRIPTIVES, CSTABULATE, CSGLM, CSLOGISTIC, or CSORDINAL procedures. 24 Complex Samples Selection (CSSELECT) — CSSELECT selects complex, probability-based samples from a population. It chooses units according to a sample design created through the CSPLAN procedure. Complex Samples Descriptives (CSDESCRIPTIVES) — CSDESCRIPTIVES estimates means, sums, and ratios, and computes their standard errors, design effects, confidence intervals, and hypothesis tests for samples drawn by complex sampling methods Complex Samples Tabulate (CSTABULATE) — CSTABULATE displays one-way frequency tables or two-way crosstabulations and associated standard errors, design effects, confidence intervals, and 1.800.253.2575 (U.S. only) Order now! hypothesis tests for samples drawn by complex sampling methods Complex Samples General Linear Model (CSGLM) — Enables you to build linear regression, analysis of variance (ANOVA), and analysis of covariance (ANCOVA) models for samples drawn using complex sampling methods ■ Main effect, all n-way interactions, and fully crossed and custom, including nested terms ■ Model parameters: Coefficient estimates, standard error for each coefficient estimate, t test for each coefficient estimate, confidence interval for each coefficient estimate, design effect for each coefficient estimate, and square root SPSS Complex Samples allowed the marketing manager to produce a more accurate model to predict customer satisfaction. As a result, the organization was able to make better business decisions. of the design effect for each coefficient estimate ■ Population means of dependent variable and covariates ■ Model fit ■ Test statistics: Wald F test, adjusted Wald F test, Wald Chi-square test, and adjusted Wald Chi-square test ■ Adjustment for multiple comparisons: Least significant difference, Bonferroni, sequential Bonferroni, Sidak, and sequential Sidak ■ Sampling degrees of freedom: Sample design or fixed by user ■ Estimated means: Requests estimated marginal means for factors and interactions in the model ■ Contrasts: Simple, deviation, Helmert, repeated, or polynomial Model variables can be saved to the active file and/or exported to external files that contain parameter matrices: Variables-predicted values and residuals, parameter covariance matrix, and its other statistics, as well as parameter correlation matrix, and its other statistics, can be exported as an SPSS data file; parameter estimates and/ or the parameter covariance matrix can be exported to an XML file ■ Sample design information ■ Regression coefficient estimates and t tests ■ Summary information on dependent variable, covariates, and factors ■ Summary information about the sample, including the unweighted ■ count and population size Confidence limits for parameter estimates and user-specified confidence levels: Wald F test for model effects, design effects, multiple R2, set of contrast coefficients (L) matrices, variance-covariance matrix of regression coefficient estimates, root mean square error, and covariance and correlation matrices for regression coefficients Complex Samples Ordinal (CSORDINAL) — CSORDINAL performs regression analysis on a binary or ordinal polytomous dependent variable using the selected cumulative link function for samples drawn by complex sampling methods ■ Models: Same as CSGLM ■ For more details and complete specifications, go to www.spss.com/complex_samples What’s New in SPSS Complex Samples 15.0 Incorporate complex sample designs into your data analysis Only SPSS Complex Samples makes understanding and working with your complex sample survey results easy. It is one of the most comprehensive software programs available. SPSS Complex Samples provides you with everything you need to produce more accurate results… ■ Logistic regression: Predict categorical outcomes (such as: Who is most likely to buy my product?) while taking the sample design into account to accurately identify groups ■ Ordinal regression: See sidebar ■ General linear models: Predict numerical outcomes while taking the sample design into account ■ Intuitive Sampling Wizard: Guides you step-by-step through the process of designing and drawing a sample ■ Easy-to-use Analysis Preparation Wizard: Helps prepare public-use datasets for analysis, such as the National Health Inventory Survey ■ ■ ■ ■ ■ Model parameters: Same as CSGLM plus exponentiated estimates, covariances of parameter estimates, and correlations of the parameter estimates Model fit: Pseudo R2 and classification table – Parallel lines tests: Wald tests of equal slopes, parameter estimates for generalized (unequal slopes) model, and covariances of parameter estimates for generalized (unequal slopes) model – Summary statistics for model Test statistics: Same as CSGLM Adjustment for multiple comparisons: Same as CSGLM Sampling degrees of freedom: Same as CSGLM ■ ■ ■ ■ ■ ■ ■ ■ ■ ■ data from the Centers for Disease Control and Prevention (CDC) Easier collaboration with colleagues: Easily share sampling and analysis plans More accurate analyses: Enables you to take up to three stages into account when analyzing data from a multistage design A more precise picture of your data: Unlike traditional statistics, subpopulation assessments take other subpopulations into account Use the following types of sample design information with SPSS Complex Samples: ■ Stratified sampling: Increase the precision of your sample or ensure a representative sample from key groups by choosing to sample within subgroups of the survey population. For example, subgroups might be a specific number of males or females or contain people in certain job categories, people of a certain age group, and so on. Model variable: Save predicted category, probability of predicted category, probability of observed category, cumulative probabilities (one variable per category), and predicted probabilities (one variable per category). Export as an SPSS data file Export as XML Three estimation methods: Newton-Raphson, Fisher Scoring, and Fisher Scoring followed by Newton-Raphson Cumulative link functions: Cauchit, complementary log-log, logit, negative log-log, and probit Cumulative odds ratios for the specified factor(s) or covariate(s) Sample design information ■ ■ Clustered sampling: Select clusters, which are groups of sampling units, for your survey. Clusters can include schools, hospitals or geographic areas with sampling units that might be students, patients, or citizens. Clustering often helps make surveys more cost-effective. Multistage sampling: Select an initial or first-stage sample Accurate analysis of survey data Sampling Plan Wizard ■ For more details and complete specifications, go to www.spss.com/complex_samples Analysis Preparation Wizard When collecting data: n Specify the sampling scheme n Draw the sample Design effects Classification table ■ Set of contrast coefficients (L) matrices ■ Variance-covariance matrix of regression coefficient estimates ■ General estimable function table ■ Correlation matrix for regression coefficients ■ User-specified denominator, df, used in computing p values for all test statistics ■ Collinearity diagnostics ■ Fits model for a subpopulation Complex Samples Logistic Regression (CSLOGISTIC) — Performs binary logistic regression analysis, as well as multinomial logistic regression (MLR) analysis, for samples drawn by ■ based on groups of elements in the population; then create a second-stage sample by drawing a sub-sample from each selected unit in the first-stage sample. By repeating this option, you can select a higher-stage sample. For example, in a face-to-face survey, you might sample individuals within households and city blocks. When working with public-use datasets: n Specify how the sample was drawn n Save and share with colleagues Plan files n Analyze data n n Results n n complex sampling methods ■ Models: Same as CSGLM ■ Model parameters: Same as CSGLM plus covariances of parameter estimates, and correlations of the parameter estimates 2 ■ Model fit: Pseudo R and classification table ■ Test statistics: Same as CSGLM ■ Adjustment for multiple comparisons: Same as CSGLM ■ Sampling degrees of freedom: Same as CSGLM ■ Model variables can be saved to the active file and/or exported to external files that contain parameter matrices – Variables: Predicted category and predicted probabilities Descriptives—Analyze measures of continuous types, including ratios Tabulate—Analyze measures of categorical types, including crosstabs Complex samples general linear model— Predict numerical outcomes Complex samples ordinal regression— Predict ordinal outcomes Complex samples logistic regression— Predict categorical outcomes Accurately predict ordinal outcomes from your complex sample design by using complex samples ordinal regression. For example, accurately predict customer satisfaction (low, medium, or high) when using sample survey methodology. Select from two simple random sampling (SRS) estimators in the Complex Samples Plan (CSPLAN) procedure: ■ WOR (without replacement) SRS variance estimator includes the finite population correction. This estimator is the default. ■ WR (with replacement) SRS variance does not include the finiteanalysis population correction. Accurate of survey data This is easy in SPSS Complex Samples. estimator is recommended when Start with one of the wizards theone analysis weights have been (which depends on your datascaled source)soand then use that they dothe not add up interface to create plans, analyze to the population size. data and interpret results. – Parameter covariance matrix and its other statistics, as well as parameter correlation matrix and its other statistics, can be exported as an SPSS data file – Parameter estimates and/or the parameter covariance matrix can be exported to an XML file ■ Sample design information ■ Summary information about the dependent variable, covariates, and factors ■ Sample summary information ■ Confidence limits for parameter estimates and user-specified confidence levels ■ Model summary statistics ■ Wald F test for model effects ■ Design effects Classification table Set of contrast coefficients (L) matrices ■ Variance-covariance matrix of regression coefficient estimates ■ Root mean square error ■ Covariance and correlation matrices for regression coefficients ■ User-specified denominator, df, used in computing p values for all test statistics ■ Collinearity diagnostics ■ Models can be fit for subpopulations System requirements ■ SPSS 15.0 for Windows ■ Other system requirements vary according to platform ■ ■ 1.800.253.2575 (U.S. only) Order now! 25 Conjoint analysis helps identify customer preferences SPSS Conjoint 15.0 ■ ■ ■ SPSS Module Identify product features important to new customers Discover which product attributes are most important to current customers Determine the influence product attributes have on customer preferences Discover what drives your customers’ purchase decisions Thoroughly understand consumer preferences, tradeoffs, and price sensitivity with SPSS Conjoint. By using conjoint analysis, you can uncover more information about how customers compare products in the marketplace and measure how individual product attributes affect consumer behavior. Armed with this knowledge, you can design, price, and market products and services tailored to your customers’ needs. SPSS Conjoint 15.0 outputs its results to pivot tables, which: Provide better, more professionallooking and presentable charts ■ Offer more formatting options than text output ■ Can be exported to Microsoft Word, Excel, or PowerPoint ■ Can be used by the SPSS Output Management System (OMS) A software firm planned to develop training programs in addition to the traditional instructor-led training. Since many options were available, they decided to perform a conjoint study to evaluate the proposed product. Six key attributes believed to influence consumer preference were identified: method of delivery, video content, types of examples, certification test, method of asking questions remotely, and price. Four of these attributes have two levels, while the other two have three. The resulting full-factorial design would have 144 alternative product bundles (2 x 2 x 2 x 2 x 3 x 3), making for an unreasonably large study. However, using the Orthoplan process in SPSS Conjoint 15.0, the researcher can reduce this down to only 16 hypothetical product bundles (such as those in Figure 1) while ensuring that they will still receive all the information needed to perform a complete analysis. Then these 16 bundles can be printed with Plancards and given to a sample of target users to rank. ■ When these preference rankings are analyzed with SPSS Conjoint, the results shown in Figure 2 are produced. Two attributes stand out as very important—inclusion of video and price—while the certification test and types of examples are relatively unimportant. The Utility and Factor columns in Figure 2 show the relative preference for each level of each attribute. Within question method, instant messaging is the most preferred and no support is the least preferred. SPSS Conjoint helps uncover answers to your critical questions: Which features or attributes of a product or service drive the purchase decision? Which feature combinations will have the most success? What market segment is most interested in the product? What marketing messages will most appeal to that segment? What is the optimal price to charge consumers for a product or service? Who are the closest competitors in the market? Figure 1 Figure 2 26 1.800.253.2575 (U.S. only) Order now! For more details and complete specifications, go to www.spss.com/conjoint How does your product rank? SPSS Conjoint provides the tools you need to find out SPSS Conjoint offers the procedures you need to plan, implement, and analyze efficient conjoint surveys. With these techniques, you can discover how respondents rank their preferences and product attributes. 2 1 Orthoplan — Produces an orthogonal array of product attribute combinations, dramatically reducing the number of questions you must ask while ensuring enough information to perform a full analysis. Plancards — Print “cards” to elicit respondents’ preferences. Quickly generate cards that respondents can sort to rank alternative products. Conjoint procedure — Get results you can act on, such as which product attributes are important and at what levels they are most preferred. Plus, perform simulations which will tell you expected market shares for alternative products. Save time and money with Orthoplan Establish the parameters of your study with the Orthoplan design generator. Orthoplan gives you an orthogonal array of alternative potential products that combine different product features at specified levels. This saves you time and money by presenting a fraction of all possible alternatives. Rank preferences Conjoint quickly guides you through creating “plan cards” that respondents sort to rank their preferences of alternative products. 3 Generate charts After you gather and input the data using your plan cards, SPSS Conjoint performs an ordinary least squares analysis of preference or rating data. It then generates charts to simulate expected market shares. For instance, in this chart you can quickly see that subjects strongly consider package design and brand name as the most important. Add SPSS Conjoint to your competitive research and develop products and services that are more successful. Product specifications Orthoplan — Generates orthogonal main effects fractional factorial designs; it is not limited to twolevel factors ■ Specify the desired number of cards for the plan; Orthoplan will try to generate a plan in the desired minimum number of runs ■ Generate holdout cards to test the fitted conjoint model ■ Orthoplan can mix the training and holdout cards or can stack the holdout cards after the training cards ■ Save the plan file as an SPSS system file ■ Pivot table output Plancards — A utility procedure used to produce printed cards for a conjoint experiment; the printed cards are used as stimuli to be sorted, ranked, or rated by the subjects ■ Specify the variables to be used as factors and the order in which their labels are to appear in the output ■ Choose a format – Listing-file format: Differentiate holdout cards from experimental cards and list simulation cards separately following the experimental and holdout cards – Card format: Holdout cards are not differentiated and simulation cards are not produced ■ Write the cards to an external file or the listing file ■ ■ Specify optional title and footer Pivot table output Conjoint — Performs an ordinary least squares analysis of preference or rating data ■ Work with the plan file generated by Plancards or a plan file input by the user using DATA LIST ■ Work with individual level rank or rating data ■ Provide individual level and aggregate results ■ Treat the factors in any of a number of ways; conjoint indicates reversals – Discrete: Factor levels are categorical – Linear: Scores or ranks are linearly related to the factor For more details and complete specifications, go to www.spss.com/conjoint ■ – Ideal: A quadratic relationship is expected between the scores or ranks and the factor; this method assumes that there is an ideal level for the factor, and that distance from the ideal point in either direction is associated with decreasing preference – Antideal: A quadratic relationship is expected between the scores or ranks and the factor; this method assumes that there is a worst level for the factor, and that distance from this point in either direction is associated with increasing preference Experimental cards have one of three scenarios: Training, ■ ■ ■ ■ holdout, and simulation Three conjoint simulation methods: Max utility; BradleyTerry-Luce (BTL); and logit Print control – Print the results of the experimental (training and holdout) data analysis – Print the results of the conjoint simulation Write utilities to an external file Print results – Attribute importance – Utility (part-worth) and standard error – Graphical indication of most to least preferred levels of each attribute ■ – Counts of reversals and reversal summary Pearson R for training and holdout data – Kendall’s tau for training and holdout data simulation results and simulation summary Pivot table output System requirements ■ SPSS 15.0 for Windows ■ Other system requirements vary according to platform 1.800.253.2575 (U.S. only) Order now! 27 Benefits of using SPSS Data Preparation: SPSS Data Preparation 15.0 Quickly identify invalid cases so you can inspect them prior to analysis Formerly known as SPSS Data Validation™ ■ ■ ■ SPSS Module Streamline the data preparation process Eliminate labor-intensive manual checks Reach more accurate conclusions Eliminate labor-intensive manual checks by performing automatic data checks based on each variable’s measure level, categorical or continuous Updated Prevent outliers from skewing a predictive model using anomaly detection prior to model building Improve data preparation for more accurate results Quickly pre-process your data to get it ready for analysis What’s New in SPSS Data Preparation 15.0 This add-on module enables you to easily identify suspicious and invalid cases, variables, and data values; view patterns of missing data; and summarize variable distributions. You can streamline the data preparation process so that you can get ready for analysis faster and reach more accurate conclusions. Reach the best possible outcome with the new Optimal Binning procedure. Now you can more accurately use algorithms designed for nominal attributes (such as Naïve Bayes and logit models). Optimal Binning enables you to bin, or set cutpoints for, scale variables. Perform automatic data checks Eliminate time-consuming, tedious manual checks by using the Validate Data procedure. This procedure enables you to apply rules to perform data checks based on each variable’s measure level (whether categorical or continuous). Then, determine data validity and remove or correct suspicious cases at your discretion prior to analysis. Select from three types of optimal binning for preprocessing data prior to model building: ■ Unsupervised: Create bins with equal counts ■ Supervised: Take the target variable into account to determine cutpoints. This method is more accurate than unsupervised; however, it is also more computationally intensive. ■ Hybrid approach: Combines the unsupervised and supervised approaches. This method is particularly useful if you have a large amount of distinct values. Quickly find multivariate outliers Easily detect multivariate outliers so you can further examine them and determine if they should be included in your analyses. The Anomaly Detection procedure searches for unusual cases based upon deviation. It enables you to flag outliers by creating a new variable. Product specifications Symbol indicates a new feature. Validate data Use the Validate Data procedure to validate data in the working data file ■ Basic checks: – Maximum percent of missing values, single category cases, and cases with a count of 1 – Minimum coefficient of variation 28 ■ – Minimum standard deviation – Flag incomplete IDs, duplicate IDs, and empty cases Standard rules: Describe the data, view single variable rules, and apply them to analysis variables – Description of data: ■ Distribution: Shows a thumbnail-size bar chart for categorical variables or histogram for scale variables ■ Min./max. data values shown – Single-variable rules: 1.800.253.2575 (U.S. only) Order now! Apply rules to identify missing or invalid values ■ User-defined Custom rules: Define crossvariable rule expressions in which respondents’ answers violate logic Output: Reports for invalid data – Casewise report, specify by case ■ Specify the minimum number of violations needed for a case ■ Specify the maximum number of cases in the report – Standard validation rules reports ■ ■ ■ Summarize violations by analysis variable and rule ■ Display descriptive statistics Save: Save variables that record rule violations and use them to clean data and filter out bad cases – Summary variables: ■ Empty case indicator ■ Duplicate ID indicator ■ Incomplete ID indicator ■ Validation rule violation – Indicator variables that record all validation rule violations ■ ■ Identify unusual cases Anomaly Detection procedure. Search for unusual cases, based upon deviations from peer group, and reasons for deviations ■ VARIABLES subcommand: Specify categorical, continuous, and ID variables, and list variables that are excluded from the analysis. ■ HANDLEMISSING subcommand: Specifies the methods of handling missing values in this procedure ■ The CRITERIA subcommand ■ specifies the following settings: – Number of peer groups – Adjustment weight on the measurement level – Number of reasons in the anomaly list – Percentage and number of cases considered as anomalies and included in the anomaly list – Cutpoint of the anomaly index to determine whether a case is considered as an anomaly Save additional variables to the For more details and complete specifications, go to www.spss.com/data_preparation Identify suspicious or invalid cases, variables, and data values easily with SPSS Data Preparation 3 2 1 Basic checks: You can specify basic checks to apply to variables and cases in your file. For example, you can obtain reports that identify variables with a high percentage of missing values or empty cases. Variables tab: The Validate Data dialog is used to validate your data. The Variables tab shows variables in your file. Start by selecting the variables you are interested in and moving them to the Analysis Variables list. Save: You can also save variables that record rule violations and can be used to help you clean your data and filter out bad cases. 6 5 4 Standard rules: Apply rules to individual variables that identify invalid values such as values outside a valid range or missing values. When you press OK, the Validate Data dialog produces reports that summarize invalid values and cases. Define custom rules: Create cross-variable rules in which respondents’ answers violate logic (such as “pregnant males”). Define standard rules: The Validate Data dialog lets you create your own rules or apply predefined rules. ■ ■ working data file including: – Anomaly index – Peer group ID, size, and size in percentage – Variable, variable impact measure, variable value, and norm value associated with a reason OUTFILE subcommand: Write a model to a filename as XML PRINT subcommand prints: – Case-processing summary – Anomaly index list, anomaly peer ID list, and anomaly reason list – The Continuous Variable Norms table, for continuous variable, and the Categorical Variable Norms, for categorical variable – Anomaly Index Summary – Reason Summary Table Optimal Binning Preprocess data with Optimal Binning. Categorizes one or more continuous variables by distributing the values of each into bins. ■ Select from the following methods: – Unsupervised binning via the equal frequency algorithm. It uses the equal frequency algorithm to discretize the binning input variables. Guide variable not required. – Supervised binning via the MDLP (Minimal Description Length Principle) algorithm. Discretizes binning input variables using the MDLP algorithm without any pre- For more details and complete specifications, go to www.spss.com/data_preparation ■ processing. Ideal for small datasets. Guide variable required. – Hybrid MDLP binning. Involves preprocessing via the equal frequency algorithm, followed by the MDLP algorithm. Ideal for large datasets. Guide variable required. Specify the following criteria: – How to define the minimum and maximum cutpoint for each binning input variable, and the ■ ■ lower limit of an interval – Whether to force-merge sparsely populated bins – Whether missing values uses listwise or pairwise deletion Save new variables with binned values and syntax to an SPSS syntax file PRINT subcommand prints: – The binning input variables’ cutpoint sets – Descriptive information for all binning input variables – Model entropy for binned variables System requirements ■ SPSS 15.0 for Windows ■ Other system requirements vary according to platform 1.800.253.2575 (U.S. only) Order now! 29 SPSS Exact Tests is crucial to your research if you are: SPSS Exact Tests 15.0 ■ ■ ■ SPSS Module “What impresses me most about SPSS Exact Tests is how it fills the deficiencies that many of the major statistics programs have in the area of nonparametric inference and hypothesis tests...” – Vincent C. Arena, Ph.D, University of Pittsburgh, Graduate School of Public Health Department of Biostatistics Product specifications Succeeds where traditional tests fail Offers more than 30 exact tests, so you can analyze rare occurrences in large datasets Ensures you’ll work more confidently with smaller sample sizes Reach accurate conclusions with small samples or rare occurrences SPSS Exact Tests is the add-on module to turn to when you’d like to analyze rare occurrences in large databases or work more accurately with small samples. With more than 30 exact tests, you’ll be able to analyze your data where traditional tests fail. With SPSS Exact Tests, you can use smaller sample sizes and be confident of your results. SPSS Exact Tests has the tests and statistics you need, including: ■ Exact p-values ■ Monte carlo p-values ■ Pearson Chi-squared test ■ Linear-by-linear association test Linear-by-linear association test Exact 1-tailed and 2-tailed p-values and exact point probability ■ Monte Carlo 1-tailed and 2-tailed p-values and CIs ■ Tests and statistics Pearson Chi-square test, Likelihood ratio test, and Fisher’s Exact test ■ Exact 1-tailed, 2-tailed p-values for 2x2 table ■ Exact 2-tailed p-values for general RxC table ■ Monte Carlo 2-tailed p-value and confidence intervals for general RxC table 30 Operating with a small number of cases Working with variables that have a high percentage of response in one category Subsetting your data into fine breakdowns Searching for rare occurrences in large datasets Contingency coefficient, Phi, Cramer’s V, Goodman and Kruskal Tau, Uncertainty coefficient— symmetric or asymmetric, Kappa, Gamma, Kendall’s Tau-b and Tau-c, Somer’s D—symmetric and asymmetric, Pearson’s R, and Spearman correlation ■ Exact 2-tailed p-value ■ Monte Carlo 2-tailed p-value and CIs 1.800.253.2575 (U.S. only) Order now! ■ ■ ■ ■ ■ Contingency coefficient Uncertainty coefficient—symmetric or asymmetric Wilcoxon signed-rank test Cochran’s Q test Binomial test Analyze small datasets and get more precise results In this example, even though there are only 10 cases, SPSS Exact Tests helps you determine that a significant relationship exists. SPSS Exact Tests ensures you’ll always have the right statistical test for your data. And because SPSS Exact Tests is part of the SPSS integrated product line, you can count on beginning-to-end solutions for your modeling and data analysis needs. McNemar test ■ Exact 1-tailed and 2-tailed p-value and point probability Sign test and Wilcoxon signed-rank test ■ Exact 1-tailed and 2-tailed p-value and point probability ■ Monte Carlo 1-tailed and 2-tailed p-values and CIs Marginal homogeneity test ■ Asymptotic, exact, Monte Carlo 1-tailed and two 2-tailed p-values, and point probability Print both asymptotic and exact p-values Note the exact p-values show statistical significance at the .05 level or less, whereas the asymptotic p-values incorrectly show nonsignificance. 2-Sample Kolmogorov-Smirnov test ■ Exact 2-tailed p-value, and point probability ■ Monte Carlo 2-tailed p-values and CIs Wald-Wolfowitz Runs test ■ Exact 1-tailed p-value and point probability ■ Monte Carlo 1-tailed p-value and CIs Mann-Whitney U or Wilcoxon Rank-sum W test ■ Exact 2-tailed p-value and exact 1-tailed p-value, and point probability ■ Monte Carlo 1-tailed and 2-tailed p-value and CIs Cochran’s Q test, Friedman test, Kendall’s coefficient of concordance, Kruskal-Wallis test, Median test, 1-Sample Kolmogorov-Smirnov test and 1-Sample Wald-Wolfowitz Runs test ■ Exact 2-tailed p-value and point probability ■ Monte Carlo 2-tailed p-values and CIs Jonckheere-Terpstra test ■ Asymptotic, exact, Monte Carlo 1-tailed and 2-tailed p-values, and point probability Binomial test Both exact 1-tailed and 2-tailed p-values, and point probability ■ System requirements SPSS 15.0 for Windows ■ Other system requirements vary according to platform ■ For more details and complete specifications, go to www.spss.com/exact_tests Four ways to expand your analysis with SPSS Maps: SPSS Maps 15.0 ■ ■ ■ Visualize your analysis geographically Pinpoint locations for profitable business sites Determine where your most profitable customers are located 1. Analyze the relevance of geographic variables 2. Interpret sales data and determine where your most profitable customers are located 3. Display sales trends, crime rates, or accident rates for specific locations 4. Discover where prospects matching your customer profiles are located Chart a course for better decision making SPSS Module SPSS Maps enables you to transform your SPSS data into demographic information. ■ With SPSS Maps, you’ll make more informed decisions because you have a clearer picture of how geographic variables can affect your organization. It integrates seamlessly with SPSS menus to provide the capabilities you need to easily turn your data into visual, easy-to-read maps. ■ Powerful visualization map plots: Add geographic analysis with dot density, bar charts, pie charts, graduated symbols, individual values box, and range of values ■ Multiple thematic layers: Combine several thematic layers and customize with photo background pictures for professional-quality, realistic maps ■ Data binding: Automatically attach data to your maps Product specifications Key features ■ Six thematic map options – Dot density: Display a number of dots for data points proportional to the area’s specific level; points may be assigned manually or let SPSS Maps plot points automatically – Bar: Display bar charts for each selected geographic area – Pie: Display pie charts for each selected geographic area – Graduated symbols: Display a symbol whose size corresponds ■ ■ to the relative level for a geographic area – Individual values box: Use color or patterns to identify categories for each area – Range of values: Display color shades for each geographic area to represent relative value Multiple thematic layers: Display more than one thematic on a single geographic map Several sample maps/geosets: Maps from all over the world are provided in MapInfo format, such as European capitals, demographics for Asia, world top 25 cities, plus much more For more details and complete specifications, go to www.spss.com/maps ■ ■ ■ ■ ■ ■ ■ ■ ■ Geoset manager: Quickly convert thirdparty maps into compatible data— mismatches are automatically converted Map summary statistics: Automatically display map summary statistics for the entire map or any selected or highlighted region Automatic chart labeling: Eliminates tedious thematic key formation Sample datasets: Includes demographic data from Claritas Inc. for quick analysis, and sample datasets from MapInfo® for instant demographic comparisons SPSS syntax editor: Offers one-click access to production mapping Flexible output: Export maps as standard graphic files for distribution almost anywhere, including the Web Import maps: Import additional maps for specialized requirements Free sample datasets: SPSS Maps is bundled with demographics, Workplace Population, PRIZM® and CLOUT™ data from Claritas Inc. Plus, more than 40 international MapInfo demographic data files help in quick demographic analysis without laborious data collection SPSS syntax programming: Produce maps with standard SPSS syntax Automatic labeling: Any graph used in presentation or publication needs labels and a key. This feature eliminates the need to ■ ■ ■ ■ manually label key elements. Undo and redo: Map creation/ editing/viewing include the ability to eliminate or redo the last editing step Zoom and unzoom: Map magnitude parameters are easy to change during viewing for quick orientation and exploration. Level of features automatically changes for proper level of detail. Projections and coordinate system: Coordinate systems and projections can be displayed on the created maps Map formatting: Choose colors and other aesthetic attributes With SPSS Maps, you can display, edit, and customize your data to produce the best map to present your message. ■ Map export tool: Export maps as standard graphic files (WMF, CGM, TIF, PICT, EPS, PNG, BMP, and JPEG) for distribution almost anywhere Supported statistics Means ■ Medians ■ Modes ■ Variances ■ Maximum values ■ Minimum values ■ Standard deviations ■ First values ■ Last values ■ Sums ■ Number of cases less than ■ ■ ■ ■ ■ ■ ■ ■ Number of cases greater than Percentage of cases less than Percentage of cases greater than Number of cases less than or equal to Percentage of cases less than or equal to Number of cases greater than or equal to Percentage of cases greater than or equal to System requirements SPSS 15.0 for Windows ■ Other system requirements vary according to platform ■ 1.800.253.2575 (U.S. only) Order now! 31 SPSS Missing Value Analysis 15.0 ■ ■ ■ SPSS Module Overcome missing data issues Reach more statistically significant results when taking missing values into account Determine the extent of missing data quickly Create higher-value data and build better models when you estimate missing data Even in the best-designed and monitored study or survey, observations can be missing—a person inadvertently skips a question, a sample or response is illegible or there are technical malfunctions. SPSS Missing Value Analysis allows you to quickly and easily diagnose your missing data and fill in the blanks to create higher-value data which result in better models. When you ignore or exclude missing data, you risk reaching invalid and insignificant results. Don’t risk invalid results! With SPSS Missing Value Analysis 15.0, you can: Diagnose if you have a serious missing data problem Replace missing values with estimates Ensure you enter the data analysis stage using data that takes missing values into account Improve survey questions—identify possibly troublesome or confusing questions, based on observed missing data patterns Draw more valid conclusions and remove hidden bias from your data Make SPSS Missing Value Analysis a part of your data management and preparation step, and you’ll enter the data analysis stage using data that takes missing values into account. Missing data: the hidden problem A consumer goods company’s primary source of customer information is a few survey questions on the warranty card returned by customers. The warranty card survey collects data on age, occupation, gender, marital status, family size, and income. The marketing department analyzes the data to better understand the demographics of their customer base to more effectively target promotions. They used SPSS Missing Value Analysis to investigate the extent of missing data. First, they produced a summary table, which gave an overview of the responses for each question. The question with the highest rate of missing data is income (34%). Further investigation reveals that 31 customers did not report occupation and income. Missing data appears to be a potential problem. SPSS Missing Value Analysis offers two methods for maximum likelihood estimation and imputation—EM (Expectation-Maximization) algorithm and regression. Both of these highly sophisticated methods can be used to inspect the results. When used by the company, these methods produced a different response than the data with missing values. Compare the results to the data with missing values: 32 1.800.253.2575 (U.S. only) Order now! Incomplete data (calculated with missing values) Largest segment: 38% married women ■ Income range: $18,000 – $42,000 ■ Occupation: any Mailing Cost per piece: $1 100,000 names purchased Total cost for mailing: $100,000 Complete data ■ Largest segment: 46% married women ■ Income range: $17,000 – $39,000 ■ Occupation: non-professional Incomplete data Response rate: 2% Total number of responses: 2,000 Closed sales: 1,000 Average revenue per sale: $100 Total revenue: $100,000 Profit: $0 ■ While these differences may appear subtle, they translate into significant cost savings. Consider the case where the marketing department purchases a list for a direct mail promotion based on these target market demographics. More people are mailed to that are outside the target market, lowering the response rate. Overall, the direct mail campaign based on complete data is more profitable. Complete data Response rate: 4% Total number of responses: 4,000 Closed sales: 2,000 Average revenue per sale: $100 Total revenue: $200,000 For more details and complete specifications, go to www.spss.com/missing_value Draw more valid conclusions with SPSS Missing Value Analysis 1 Product specifications It’s easy for you to evaluate the affect of missing data, especially with small datasets, because SPSS Missing Value Analysis offers the features and benefits below. Discover missing data Six tailor-made displays: Examine data from several angles using six diagnostic reports to uncover missing data patterns. Diagnose missing data problems: Get a case-bycase overview of your data with the data patterns report. By giving you a snapshot of each type of missing value and any extreme values for each case, you can determine the extent of missing data quickly. First, investigate where the missing values are located and how extensive they are. This summary tables shows 31.2% of the cases are missing daily calorie intake values. 2 Better summary statistics: Adjust for missing values so you get a more accurate description of your data. Choose from four methods: listwise deletion, pairwise deletion, EM, and covariance matrix. Detect patterns in your data Fill in missing data: Easily replace missing values with estimates and increase your chance of reaching statistically significant results. Choose from the EM and regression algorithms to predict missing values based on data you already have. 3 Powerful and accurate analysis, with all cases represented Next, explore patterns of missing data. Here, the missing value patterns show a large discrepancy in GDP. The GDP per capita is $3,108 for the 59 countries with no missing data and $16,554 for the 15 counties where Literacy_Male and Literacy_Female are missing. Analyze patterns ■ Display missing data and extreme cases for all cases and all variables using the data patterns table – Displays system missing and three types of user-defined missing values – Sort in ascending or descending order – Display actual values for specified variables ■ Display patterns of missing values for all cases that have at least one missing value using the missing patterns table – Group similar missing value patterns together – Sort by missing patterns and variables ■ Determine differences between missing and non-missing groups for a related variable with the separate variance t test table ■ Show differences between present and missing data for categorical variables using the distribution of categorical variables table ■ Assess how much missing data for one variable relates to the missing data of another variable using the percent mismatch of patterns table – Sort matrices by missing value patterns or variables ■ Identify all unique patterns with the tabulated patterns table, which summarizes each missing data pattern and displays the count for each pattern plus means and frequencies for each variable – Display count and averages for each missing value pattern using the summary of missing value patterns table Statistics Univariate: Compute count, mean, standard deviation, and standard error of mean for all cases excluding those containing missing values, count and percent of missing values, and extreme values for all variables ■ Listwise: Compute mean, covariance matrix, and correlation matrix for all quantitative variables for cases excluding missing values ■ Pairwise: Compute frequency, mean, variance, covariance matrix, and correlation matrix ■ EM algorithm – Estimate the means, covariance matrix, and correlation matrix of quantitative variables with missing values, assuming normal distribution, t-distribution with degrees of freedom, or a mixednormal distribution with any mixture proportion and any standard deviation ratio ■ Regression algorithm – Estimate the means, covariance matrix, and correlation matrix of variables set as dependent; set number of predictor variables; and set random elements as normal, t, residuals, or none Data management ■ Handle all character variables as categorical variables ■ Use the first eight characters of a string variable when defined as categorical ■ Save the completed data matrix as an external file System requirements ■ SPSS 15.0 for Windows ■ Other system requirements vary according to platform ■ Estimate means, standard deviations, covariances, and correlations using listwise (complete cases only), pairwise, EM, and/or regression methods—so that all cases are represented in your analysis. Here, the estimated means using the four estimation methods are shown in a summary table. For more details and complete specifications, go to www.spss.com/missing_value 1.800.253.2575 (U.S. only) Order now! 33 Logistic regression helps target the right customers and increase profits SPSS Regression Models 15.0 ■ ■ ■ Predict categorical outcomes with more than two categories Easily classify your data into two groups Updated Gain more control over your model Make better predictions with powerful regression procedures SPSS Module SPSS Regression Models, an add-on module for SPSS, gives you an even wider range of statistics so you can get the most accurate response for specific data types. Do you build predictive models but find ordinary least squares regression too limiting? If so, SPSS Regression Models can make your life easier. Use SPSS Regression Models for: ■ ■ ■ ■ Market research: Study consumer buying habits Medical research: Study response to dosages Loan assessment: Analyze good and bad credit risks Institutional research: Measure academic achievement tests SPSS Regression Models is crucial to your research if… You need to predict a categorical outcome The relationship between the outcome and a set of predictors is thought to be nonlinear Your data violates the assumptions of linear regression What’s New in SPSS Regression Models 15.0 ■ ■ 34 Gain improved diagnostics in the classification table within the multinomial logistic regression (MLR) procedure. Determine how well you’ve classified data. Previously, you might have checked your work by using crosstabs. With improved diagnostics, you can omit this step. 1.800.253.2575 (U.S. only) Order now! A mail-order bookstore is seeking to increase the average dollar value of its orders. By increasing the size of each order, the bookseller can increase profits significantly—especially since their fixed costs are covered by the current product cost. Since mailing to the entire customer database is costly, the bookseller wants to identify customers most likely to accept the offer. This way it can target future promotions specifically to these customers (high-value) and yield a higher profit while incurring moderate promotional costs. It did this by taking a closer look at customers’ past transaction history and identifying if they responded to past promotions driving a high-value purchase. To identify potential high-value customers, the bookseller used the technique, binary logistic regression, to model customer response to the promotion. They found the following variables to have significant value for predicting which customers were more likely to respond to the promotion: ■ Total dollars spent on products in the previous year ■ Items purchased for children in the past year (none, under $30, more than $30) ■ Number of bestsellers purchased in the past three months (none, one, or more than one) These variables formed the basis for a model that the bookseller used to score each customer in its database for likelihood to respond to a promotion. The bookseller used these scores to rank customers and identify the best prospects for the promotion. Then they could target a mailing to these individuals. In addition, management was able to review the findings and discovered that customers who made purchases in the children’s category and those who purchased several bestsellers in a short period of time were particularly good prospects for large purchases. By gaining better insight into their customers’ behaviors and needs, they could more accurately plan and target future ads and promotions. For more details and complete specifications, go to www.spss.com/regression Find the best predictor from dozens of possibilities Apply more sophisticated models with SPSS Regression Models’ wide range of nonlinear modeling procedures. ■ Multinomial logistic regression (MLR): Predict categorical outcomes with more than two categories. Free of constraints such as yes/no answers, MLR allows you to model which factor predicts if the customer buys product A, B, or C. – Stepwise function in MLR: Save time and easily find the best predictors for your data Choose from four methods for choosing predictors: forward entry, backward elimination, forward stepwise, and backward stepwise Use Score and Wald methods for a faster and more accurate conclusion for variable selection – Apply a highly scalable, high-performance algorithm to handle big datasets – Save time by specifying the reference category in your outcome variable in the user interface. You no longer need to recode the dependent variable set up in the desired reference category. – Use Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) to better assess model fit ■ Binary logistic regression (BLR): Predict dichotomous variables such as buy or not buy, vote or not vote. This procedure offers many stepwise methods to select the main and interaction effects that best predict your response variable. ■ ■ ■ ■ Nonlinear regression (NLR) and constrained nonlinear regression (CNLR): Get control over your model and your model expression. These procedures give you two methods for estimating parameters of non-linear models. Weighted least square regression (WLS): Give more weight to measurements within a series Probit analysis (PROBIT): Analyze potency of responses to stimuli, such as medicine doses, prices, or incentives. Probit evaluates the value of the stimuli using a logit or probit transformation of the proportion responding. ■ The multinomial logistic regression procedure predicts a categorical outcome such as “primary reason for Web use.” The categories shown in this example are: a) work only, b) shopping only, c) both working and shopping, and d) neither (reference category). Search engine use was a better predictor of “shopping only” than print media use. Search engine users were 1.837 times more likely to use the Web for “shopping only” purposes than were non-users of search engines. Powerful regression procedures at work in the wireless industry 1 2 Build predictive models Predict the presence or absence of a characteristic/ outcome based on values of a set of predictor variables. In this example, a wireless telephone service provider is interested in identifying dissatisfied customers so they can intervene before they defect and switch to a competitor. For more details and complete specifications, go to www.spss.com/regression Predict categorical outcomes Use the binary logistic regression procedure to test the impact of service offers (new or expanded) on customer satisfaction. The classification table indicates that this model can correctly predict satisfaction with 90% accuracy. Product specifications Symbol indicates a new feature. Multinomial logistic regression ■ Control the values of the algorithm-tuning parameters using the CRITERIA subcommand ■ Include interaction terms ■ Customize hypotheses by directly specifying null hypotheses as linear combinations of parameters using the TEST subcommand ■ Specify a dispersion scaling value with SCALE subcommand ■ Build equations with or without a constant ■ Use a confidence interval for odds ratios ■ Save the following statistics: Predicted probability, predicted response category, probability of the predicted response category, and probability of the actual response category ■ Find the best predictor from dozens of possible predictors using stepwise functionality ■ Use Score and Wald methods, to quickly reach results with a large number of predictors ■ Assess model fit using Akaike information criterion (AIC) and Bayesian information criterion (BIC; also called Schwarz Bayesian Criterion, or SBC) ■ Diagnostics for the classification table: – Percent concordance – Percent ties – Percent discordance – C-value for logistic mode – Somer’s D – Gamma – Tau-a statistics Binary logistic regression (BLR) ■ Forward/backward stepwise and forced entry modeling ■ Transform categorical variables by using deviation contrasts, simple comparison, difference (reverse Helmert) contrasts, Helmert contrasts, polynomial contrasts, comparison of adjacent categories, user-defined contrasts, or indicator variables ■ Criteria for model building: Probability of score statistic for entry, probability of Wald, or likelihood ratio statistic for removal Save the following statistics: Predicted probability and group, residuals, deviance values, logit, Studentized and standardized residuals, leverage value, analog of Cook’s influence statistic, and difference in Beta ■ Export the model using XML Constrained nonlinear regression ■ Save predicted values, residuals, and derivatives ■ Choose numerical or userspecified derivatives Nonlinear regression (NLR) ■ Specify loss function options ■ Use bootstrap estimates of standard errors Weighted least squares (WLS) ■ Calculate weights based on source variable and Delta values or apply from an existing series ■ Output for calculated weights: Log-likelihood functions for each value of Delta; R, R2, adjusted R2, standard errors, analysis of variance, and t tests of individual coefficient for Delta value with maximized log-likelihood function ■ Display output in pivot tables Two-stage least squares (2SLS) ■ Structural equations and instrumental variables ■ Control for correlations between predictor variables and error terms ■ Display output in pivot tables Probit ■ Transform predictors: Base 10, natural, or user-specified base ■ Natural response rate estimates or specified ■ Algorithm control parameters: Convergence, iteration limit, and heterogeneity criterion probability ■ Statistics: Frequencies, fiducial confidence intervals, relative median potency, test of parallelism, plots of observed probits, or logits ■ Display output in pivot tables System requirements ■ SPSS 15.0 for Windows ■ Other system requirements vary according to platform ■ 1.800.253.2575 (U.S. only) Order now! 35 Maximize your time with SPSS Tables SPSS Tables 15.0 ■ ■ ■ Quickly create tables with a drag-and-drop interface Preview tables as you create them to get it right the first time Customize tables to make it easier for your audience to understand Create custom tables in no time SPSS Module SPSS Tables, the add-on reporting module for SPSS for Windows, enables you to turn your analysis into high-quality tabular reports. Easily display your data analysis in presentation-quality, production-ready tables. With SPSS Tables, you have the features you need to easily create and work with tabular reports: ■ Preview tables as you build them: Preview your table as you select variables and table options with a simple drag-and-drop interface, and take the guesswork out of table building ■ Control your table output: Choose from a variety of formats to represent multiway information in a two-way table and generate the view you want ■ Customize your table structure: Exclude specific categories, display missing value cells, and add subtotals to your table ■ Get in-depth analyses: Run Chi-square, column proportions, and column means ■ tests, and add more insight to your tables to identify differences, changes, or trends in your data Automate frequent reports: Run large production jobs and complex table structures with ease to automatically build similar tables with new data Build tables interactively Generate the table you envision using the Graphical User Interface (GUI). Easily work with output and present survey results by using nesting, stacking, and multiple response categories. Handle missing values and change labels and formats—even include missing values in your results. M atthew Liao-Troth, assistant professor of management, has to juggle a heavy research workload with teaching. But Liao-Troth has found that he can maximize his research time and cover more ground in the classroom by using SPSS for Windows and the SPSS Tables module. Liao-Troth describes his experience working with SPSS Tables. “ I really noticed a difference when I added the SPSS Tables module to SPSS for Windows. It is so easy to use—what used to take hours, now takes me less than five minutes. SPSS Tables has not only helped with my regular research, but it’s made a big difference in how I teach. “For example, last quarter I was demonstrating the gender effects on salary negotiations in one of my core business classes. Thanks to SPSS and the SPSS Tables module, in a one-and-a-half-hour class I was able to run the simulation, enter the data, put it into tables, create graphs, and run the statistical tests. Instead of describing to students what the tables might look like hypothetically, we were able to discuss the actual outcomes and concentrate on what we could learn from the statistical tests.” – Matthew Liao-Troth, Assistant Professor of Management, Western Washington University SPSS Tables makes report creation as easy as 1–2–3! Preview tables as you build them with SPSS Tables’ drag-and-drop capabilities and a preview pane Display information the way you want with SPSS Tables’ category management features Give your readers reports that let them dig into the information—and make more informed decisions—with SPSS Tables’ inferential statistics Share results more easily with interactive pivot tables—quickly export to Word or Excel Save time and effort by automating frequent reports using SPSS Tables’ syntax and automation in production mode 36 1.800.253.2575 (U.S. only) Order now! For more details and complete specifications, go to www.spss.com/tables Create presentation-quality tables from SPSS data—in a snap 1 Work with SPSS data seamlessly and easily 2 Customize your table to show the information you need Create your table and easily export your results 3 Once all your variables are in place, push the “OK” button to create your final table. Apply the optional TableLooks™ for a more polished appearance Add summary statistics, inferential stats, and subtotals to make it easier to understand results. Export your final output to Word or Excel. Your formatting remains intact and you can insert any additional content to describe your tables. This example shows a final report in Word. Start with your SPSS data. SPSS Tables works seamlessly in the SPSS environment so you can easily turn your data into presentation-quality tables in no time. Drag and drop your variables on the table preview builder and see what your table looks like as you create it. Product specifications Graphical user interface ■ Simple drag-and-drop table builder interface allows you to preview tables as you select variables and options ■ Single, unified table builder instead of multiple menu choices and dialog boxes for different table types Control contents ■ Create tables with up to three display dimensions: Rows (stub), columns (banner), and layers ■ Nest variables to any level in all dimensions ■ Crosstabulate multiple independent variables in the same table Add additional variables by dragging and placing them where you want. Display frequencies for multiple variables side-by-side with tables of frequencies ■ Display all categories when multiple variables are included in a table even if a variable has a category without responses ■ Display multiple statistics in rows, columns, or layers ■ Place totals in any row, column, or layer ■ Create subtotals for subsets of categories of a categorical variable ■ Custom control over category display order and ability to selectively show or hide categories Statistics ■ Select from over 40 summary statistics ■ For more details and complete specifications, go to www.spss.com/tables Calculate statistics for each cell, subgroup, or table ■ Calculate percentages at any or all levels for nested variables ■ Calculate counts and percentages for multiple-response variables based on the number of responses or the number of cases ■ Select percentage bases for missing values to include or exclude missing responses Formatting controls ■ Sort categories by any summary statistic in the table ■ Hide the categories that make up subtotals—remove a category from the table without removing it from the subtotal calculation ■ Directly edit any table element, ■ ■ ■ ■ ■ ■ ■ ■ ■ ■ ■ including formatting and labels Sort tables by cell contents in ascending or descending order Automatically display labels instead of coded values Specify minimum and maximum width of table columns (overrides TableLooks) Show a name, label, or both for each table variable Display missing data as blank, zero, “.”, or any other user-defined term Add titles and captions Output as SPSS pivot tables Specify corner labels Customize labels for statistics Display the entire label for variables, values, and statistics ■ ■ ■ ■ ■ ■ ■ Choose from a variety of numerical formats Apply pre-formatted TableLooks Define the set of variables that are related to multiple response data and save it with your data definition for subsequent analysis Accepts both long- and short-string elementary variables Imposes no limit on the number of sets that can be defined or the number of variables that can exist in a set Tests of significance: – Chi-square – Column means – Column proportions Exclude categories from significance tests Significance tests for multiple response variables Syntax and printing formats ■ Simpler, easy-to-understand syntax ■ Syntax converter (for upgrade users) ■ Specify page layout: Top, bottom, left and right margins, and page length ■ Use the global break command to produce a table for each value of a variable when the variable is used in a series of tables System requirements ■ SPSS 15.0 for Windows ■ Other system requirements vary according to platform ■ 1.800.253.2575 (U.S. only) Order now! 37 With SPSS Trends 15.0, you can: SPSS Trends 15.0 ■ ■ ■ Develop reliable forecasts quickly, regardless of the size of the dataset or number of variables In-depth support for time-series analysis Find the best model for your data using the new Expert Modeler Apply saved models to “what-if” scenarios to optimize your decisions Update and manage forecasting models efficiently Reduce forecasting error by automating appropriate model selection and parameters Gain more control over choices affecting models, parameters, and output Build expert time-series forecasts— in a flash SPSS Module Time-series analysis is the most powerful procedure you can use to analyze historical information, build models, predict trends, and forecast future events. SPSS Trends 15.0 is the best way to quickly create powerful forecasts with confidence. With better forecasts, longterm goals can be set—with insight on how to achieve them—based on your organization’s past performance and knowledge of your industry. Unlike spreadsheet programs, SPSS Trends has the advanced statistical techniques you need in order to work with time-series data. But you don’t need to be an expert statistician to use it. Regardless of your level of experience, you can analyze historical data and predict trends faster, and deliver information in ways that your organization’s decision makers can understand and use. Product specifications TSMODEL Model a set of time-series variables by using the Expert Modeler or specifying the structure of an ARIMA or exponential smoothing model ■ Allow Expert Modeler to select the best fitting predictor variables and models 38 ■ – Limit search space to only ARIMA or only exponential smoothing models – Treat independent variables as events Specify custom ARIMA models – Produces maximum likelihood estimates for seasonal and non-seasonal univariate models – General or constrained models specified by auto-regressive or moving average order, order of differencing, seasonal autoregressive, or moving 1.800.253.2575 (U.S. only) Order now! Deliver high-resolution graphs and communicate results effectively SPSS Trends 15.0 will help you find answers to tough questions: ■ If I increase my advertising budget, how will it affect sales by product or region? ■ How will increasing assembly line capacity affect production? ■ Will a change in fees affect the number of new customers we gain? ■ How will tuition increases affect enrollment? ■ ■ If you’re experienced at forecasting, SPSS Trends allows you to: ■ Control every parameter when building your data model ■ Or use SPSS Trends’ Expert Modeler recommendations as a starting point or to check your work If you’re new to building models from timeseries data, SPSS Trends helps you by: ■ Generating reliable models, even if you’re not sure how to choose exponential smoothing parameters or ARIMA orders, or how to achieve stationarity ■ Automatically testing your data for seasonality, intermittency, and missing values, and selecting appropriate models average order, and seasonal differencing – Two dependent variable transformations: Square root and natural log – Automatically detect or specify outliers: Additive, level shift, innovational, transient, seasonal additive, local trend, and additive patch – Specify seasonal and nonseasonal numerator, denominator, and difference transfer function ■ orders and transformations for each independent variable Specify custom exponential smoothing models – Four non-seasonal model types: Simple, Holt’s linear trend, Brown’s linear trend, and damped trend – Three seasonal model types: Simple seasonal, Winters’ additive, and Winters’ multiplicative – Two dependent variable transformations: Square root and natural log Detecting outliers and preventing them from influencing parameter estimates Generating graphs showing confidence intervals and the model’s goodness of fit ■ ■ ■ Display forecasts, fit measures, Ljung-Box statistic, parameter estimates, and outliers by model Generate tables and plots to compare statistics across all models Eight goodness of fit measures available: stationary R2, R2, root mean square error, mean absolute percentage error, mean absolute error, maximum absolute percentage error, maximum absolute error, and normalized BIC ■ ■ Tables and plots of residual autocorrelation function (ACF) and partial autocorrelation function (PACF) Plot observed values, forecasts, fit values, confidence intervals for forecasts, and confidence intervals for fit values for each series For more details and complete specifications, go to www.spss.com/trends SPSS Trends 15.0 provides tremendous flexibility in creating forecasts with Expert Modeler. Expert Modeler: This feature was specifically designed to support forecasting with time-series data. Now you can produce time-series models even if you have little or no experience with timeseries data. This screenshot of the time-series modeler shows how it provides you with the ability to model multiple series simultaneously. Because the module presents results in an organized fashion, you can concentrate on the models that need closer examination. 1 The Expert Modeler feature enables you to: ■ Automatically determine the best-fitting ARIMA (autoregressive integrated moving average process) or exponential smoothing model for your time-series data ■ Model hundreds of different time series at once, rather than having to run the procedure for one variable at a time ■ Test your data for seasonality, intermittency, missing values, and outliers 2 Also in SPSS Trends 15.0: ■ Save models to an XML file so that forecasts can be updated without having to reset parameters or re-estimate the model ■ Write scripts so that updates can be performed automatically This screenshot displaying a forecast for women’s apparel shows how you can automatically determine which model best fits your time-series and independent variables. ■ ■ ■ ■ Filter output to fixed number or percentage of best or worst fitting models Save predicted values, lower confidence limits, upper confidence limits, and noise residuals for each series back to the data set Specify forecast period, treatment of user-missing values, and confidence intervals Export models to an XML file for later use by TSAPPLY TSAPPLY Apply saved models to new or updated data ■ Simultaneously apply models from multiple XML files created with TSMODEL ■ Re-estimate model parameters and goodness of fit measures from the data or load from the saved model file ■ Selectively choose saved models to apply For more details and complete specifications, go to www.spss.com/trends ■ ■ ■ Override the periodicity (seasonality) of the active dataset Same output, fit measure, statistics, and options as TSMODEL Export re-estimated models to an XML file SEASON Estimates multiplicative or additive seasonal factors for periodic time series ■ ■ Multiplicative or additive model Moving averages, ratios, seasonal and seasonal adjustment factors, seasonally adjusted series, smoothed trend-cycle components, and irregular components SPECTRA Decomposes a time series into its harmonic components, a set of regular periodic functions at different wavelengths or periods ■ ■ ■ ■ Produces/plots univariate or bivariate periodogram and spectral density estimate Bivariate spectral analysis Smooth periodogram values with weighted moving averages Spectral data windows available for smoothing: Tukey-Hamming, Tukey, Parzen, Bartlett, equal weight, no smoothing, and user-specified weights ■ High-resolution charts available: Periodogram, spectral and cospectral density estimate, squared coherency, quadrature spectrum estimate, phase spectrum, cross amplitude, and gain System requirements SPSS 15.0 for Windows ■ Other system requirements vary according to platform ■ 1.800.253.2575 (U.S. only) Order now! 39 With SPSS Server you can: SPSS Server 15.0 ■ ■ ■ Updated Analyze massive data files faster Increase analysis speed and productivity Use system resources efficiently Maximize productivity with SPSS Server In addition to analytical tools for the desktop, SPSS Inc. offers you an enterprise-level solution—SPSS Server 15.0. With SPSS Server, you can help your organization deliver enterprise-strength scalability and enhanced performance. You’ll benefit from added speed, accessibility, scalability, and data centralization. Increase productivity and facilitate decision making When you combine the strength of SPSS Inc. world-class analytical tools and techniques with the flexibility and speed of server functionality, you have a powerful solution for supporting better decision making throughout your organization. Also in SPSS Server 15.0 ■ ■ ■ Reduce network traffic and improve performance with the data-free client feature Score new data in the scoring engine using previously created models via the interface or syntax Use Feature Selection and Naïve Bayes analysis when working with large datasets For more information about SPSS Server, visit www.spss.com/spss_server or call 1.800.253.2575 (U.S. only) and speak to an SPSS representative. World’s largest mail-order wine company picks up the speed D irect Wines, the world’s largest mail order wine company, is an experienced database user. However over time it ultimately found that its existing systems could not cope with the volume and number of mailings. When searching the market, Jon White, Direct Wines customer database analyst, said, “We were looking for a huge leap in function and greater flexibility to do the things we wanted to do without being dictated to by the limitations of the system. We also wanted a system that would be user friendly and not too statistical, so that non-expert users could take advantage of it.” 40 1.800.253.2575 (U.S. only) Order now! Direct Wines has a server running SPSS Server and three workstations running the client version. SPSS is also used as the data-retrieval system. White stated, “We could not have grown as a company without SPSS.” He adds, “At first sight, SPSS has an interface with many different statistics options and transformation tools. However, the speed of its transformation and manipulation is staggering, and its ability to store syntax and scripts allows analysis to be repeated many times with ease.” Process data on the server, rather than on your client machine Access data directly from the server and free up desktop resources Ensure security with secure sockets layer (SSL) protocol and by requiring a login and password for server access Increase the tools available for preparing data and creating reports using features unique to the server version of SPSS What’s new in SPSS Server 15.0 Several new features and enhancements help your enterprise increase its productivity. Realize faster data preparation and analysis ■ Seamlessly utilize third-party multithreaded sorting applications to speed up data preparation ■ Gain increased performance when temporary files are striped over multiple disks based on the network administrator’s settings. This provides much greater speed in reading and writing large temporary files, which are often associated with time-consuming tasks such as sorting and aggregation. Remove the need for multiple administration tools ■ If you’re a network administrator, use a single Administrative Utility for working with SPSS Server, Clementine Server, and SPSS Predictive Enterprise Services™. With this utility, you can administer just one, or any combination of these three products installed at your site. For more details and complete specifications, go to www.spss.com/spss_server Complete the Picture with SPSS Stand-alone Products Amos ■ AnswerTree ■ Data Entry ■ SamplePower ■ Smart Viewer Web Server ■ Clementine ■ Dimensions ■ Amos ■ AnswerTree ■ Data Entry SamplePower ■ SmartViewer Web Server ■ Clementine ■ Dimensions ■ Amos ■ Answer Tree ■ Data Entry ■ Sample Power ■ SmartViewer Web Web Server ■ Clementine ■ Dimensions ■ “With SPSS products, I can focus on areas of analysis that have been ignored in the past. We’re now actually using the data we are collecting.” It doesn’t matter what industry you are in—it’s crucial that you collect all the necessary data and analyze it to its fullest extent. That way, you are sure to get the most complete picture and not just a snapshot of your data. SPSS offers additional software tools that can be used alone or along with SPSS for Windows. They work seamlessly together to allow you to expand your capabilities for a more complete analytical system. Check out some of the predictive analytics software that is at the cutting-edge of information technology today on the following pages. For more details and complete specifications, go to www.spss.com/spss/family.cfm – Brian C. Maclachlan, Principal Adviser, Statistical Research and Analysis, Queensland Fire and Rescue Authority Here are a few of SPSS’ most popular stand-alone products: Amos 7.0 — Allows you to easily perform structural equation modeling (SEM) to support your research and theories by extending standard multivariate analysis methods AnswerTree 3.1 — Build better profiles, discover segments, and target the right groups using powerful decision-tree algorithms SPSS Data Entry 4.0 — A complete system for collecting and managing survey research data SamplePower 2.0 — Save time, effort and money by identifying the sample size you need SmartViewer Web Server 5.0 — Deploy SPSS results with interactive Web reporting Clementine Desktop — Quickly add the power of data mining to your analysis mrInterview 3.5 and mrTables 3.5 — A complete solution for survey analysis 1.800.253.2575 (U.S. only) Order now! 41 Amos 7.0 ■ ■ ■ NEW version Easily perform structural equation modeling (SEM) Quickly create models to verify how your variables affect each other Move beyond regression to gain additional insight Take your analysis to the next level Whether you’re performing a program evaluation or developing attitudinal and behavioral models, sometimes analysis using traditional statistical correlations just isn’t going to cut it. Many researchers are turning to structural equation modeling (SEM) and Amos software to go beyond traditional techniques to explore complex relationships and more terms in their models. Gain new insights by identifying important latent variables and conclusions Amos builds models that more realistically reflect complex relationships because any numeric variable, whether observed (such as non-experimental data from a survey) or latent (such as satisfaction and loyalty) can be used to predict any other numeric variable. You can gain additional insight into the causal nature and strength of the relationships among variables. Amos makes structural equation modeling easy Amos’ rich, visual framework enables you to easily compare, confirm, and refine models. Quickly build graphical models using Amos’ simple drag-and-drop drawing tools. Models that used to take days to create are just minutes away from completion. And once the model is finished, simply click your mouse and assess your model’s fit. Then make any modifications and print a presentation-quality graphic of your final model. Obtain Bayesian estimates of model parameters and other quantities Bayesian analysis enables you to apply your subject-area expertise or business insight to improve estimates by specifying an informative prior distribution. Markov chain Monte Carlo (MCMC) is the underlying computational method for Bayesian estimation. Why Amos is the first choice for SEM… Easy-to-use interface: Just point, click, and drag, and drop to build your model—no need to type commands or write equations Quickly find models that fit your data: Select one yourself or use exploratory SEM to choose a model from a large number of candidates Easily create models in Amos: Test hypotheses and confirm relationships among observed and latent variables Discover unexpected relationships using path diagrams: Gain valuable insight into the causal nature and strength of the relationship among variables What’s new in Amos 7.0 Amos 7.0 continues to expand your statistical options based on Bayesian estimation. The MCMC algorithm is faster and the MCMC tuning parameter can now be adjusted automatically. You can now perform estimation with ordered-categorical and censored data. This enables you to: ■ ■ ■ ■ Create a model based on non-numerical data without having to assign numerical scores to the data Work with censored data without having to make assumptions other than the assumption of normality Impute numerical values for ordered-categorical and censored data. The resulting dataset can be used as input to programs that require complete numerical data. Determine probable values for missing or partially missing data values in a latent variable model Impute missing values or latent variable scores Choose from three data imputation methods: regression, stochastic regression, or Bayesian. Use regression imputation to create a single completed dataset. Use stochastic regression imputation or Bayesian imputation to create multiple imputed datasets. You can impute missing values or latent variable scores. Programming environment allows users to expand capabilities Amos lets you specify models non-graphically by writing programs with Visual Basic or C#. 42 1.800.253.2575 (U.S. only) Order now! For more details and complete specifications, go to www.spss.com/amos Amos makes structural equation modeling easy and accessible Structural equation modeling’s approach to multivariate analysis encompasses and extends standard methods—including regression, factor analysis, correlation, and analysis of variance. Amos makes SEM easy. It’s the perfect modeling tool for a variety of purposes, including: ■ ■ ■ 1 Market research — Analyze customer satisfaction, brand loyalty, or purchase behavior Business planning — Create econometric and financial models and analyze factors affecting workplace job attainment Academic program evaluation — Evaluate program outcomes or behavioral models using SEM to replace traditional stepwise regression 3 Select a data file 4 View output Select the analysis properties you wish to examine, such as standardized estimates of parameters or squared multiple correlations. Constrain parameters for more precise models by directly specifying path coefficients. Symbol indicates a new feature. Modeling capabilities ■ Create structural equation models (including such special cases as path analysis and longitudinal data models) with observed and latent variables ■ Specify candidate models using one of two methods: – Specify each individual candidate model as a set of equality constraints on model parameters – Use SEM in an exploratory way. Amos tries out many models and suggests promising ones, ■ ■ ■ ■ while using Akaike information criterion (AIC) and Bayes information criterion (BIC) statistics to compare models. Fit confirmatory factor analysis models, variance components models, errors-in-variables models, and general latent variable models Analyze data from several populations at once Save time by combining factor and regression models into a single model, and then fit them simultaneously Analyze multiple models simultaneously: Amos determines which models are nested and automatically calculates test statistics For more details and complete specifications, go to www.spss.com/amos Bayesian estimation ■ Fit models with ordered-categorical and censored data ■ Markov chain Monte Carlo (MCMC) simulation ■ Specify an informative prior distribution: Normal, uniform, or custom Computationally intensive modeling ■ Evaluate parameter estimates with normal or non-normal data using powerful bootstrapping options. The bootstrapping and Monte Carlo capabilities in Amos make it easy for you to obtain bias and standard-error estimates for any parameter, including standardized coefficients and effect estimates. ■ Test multivariate normality and perform outlier analysis Specify your model Use drag-and-drop drawing tools to quickly specify your path diagram model. Click on objects in the path diagram to edit values, such as variable names and parameter values. Or, simply drag variable names from the variable list to the object in the path diagram to specify variables in your model. Input data from a variety of file formats (SPSS, Excel, text files, or many others). Select grouping variables and group values. Amos also accepts data in a matrix format if you’ve computed a correlation or covariance matrix. Select analysis properties Product specifications 2 Amos output provides standardized or unstandardized estimates of covariances and regression weights as well as a variety of model fit measures. Hotlinks in the help system link to explanations of the analysis in plain English. 5 Assess your model’s fit Make any modifications to your model and print publication-quality output. Analytical capabilities and statistical functions ■ Determine probable values for missing or partially missing data values in a latent variable model ■ Use full information maximum likelihood estimation in missing data situations for more efficient and less biased estimates ■ Obtain an approximate confidence interval for any model parameter under any empirical distribution, including standardized coefficients, using fast bootstrap simulation – Assess model fit with Bollen and Stine’s bootstrap approach – Calculate percentile intervals and bias-corrected percentile intervals ■ Perform randomized permutation ■ ■ ■ ■ tests to show whether equivalent or better-fitting models can be found Estimate means for exogenous variables Recalculate the degrees of freedom after adding new elements or changing model constraints Use a variety of estimation methods, including maximum likelihood, unweighted least squares, generalized least squares, Browne’s asymptotically distribution-free criterion, and scale-free least squares Evaluate models using more than two dozen fit statistics, including Chi-square; AIC; Bayes and Bozdogan information criteria; Browne-Cudeck (BCC); ECVI, RMSEA, and PCLOSE criteria; root mean square residual; Hoelter’s critical n; and Bentler-Bonett and Tucker-Lewis indices Data imputation ■ Impute numerical values for orderedcategorical and censored data ■ Impute missing values and latent variable scores ■ Choose from three different methods: Regression, stochastic regression, and Bayesian ■ Single or multiple imputation System requirements ■ Operating system: Microsoft Windows XP or 2000 ■ Memory: 256MB RAM minimum ■ Minimum free drive space: 125MB ■ Web browser: Internet Explorer 6 1.800.253.2575 (U.S. only) Order now! 43 AnswerTree 3.1 ■ ■ Server available ■ High marks awarded to AnswerTree Profile customer, citizen, or student groups easily T he Lafourche Parish School Board in Thibodaux, Louisiana, wanted to measure progress by improving test scores, then use those test results to enhance learning for students in their region. Chris Bowman, Technology Manager of Lafourche Parish School Board, was commissioned to assist the local board with this reform initiative. Effectively target the right groups of people for your sales and marketing campaigns Choose from four decision-tree algorithms Target the right people more effectively using intuitive decision trees Whether you have a limited statistical background or you’re a statistician, AnswerTree will work for you. AnswerTree creates decision trees so you can easily identify the groups that matter most and understand the attributes that influence their responses. AnswerTree eliminates the costly guesswork that leads you to send offers to arbitrary people on your mailing list. Take your analysis and modeling to a new level with these features: ■ ■ ■ Works with your existing system: AnswerTree can stand-alone or can launch from within SPSS. It reads SPSS files and ODBC-compliant sources. Highly visual decision trees: Spot segments and patterns in your data quickly. Easily expand and collapse branches; zoom to nodes of interest; and use summary statistics, gain charts, and evaluation graphs to reach conclusions quickly. Interactive tree growth: When making adjustments to a tree, the model is affected and the tree is redrawn immediately Four algorithms: Find the best fit for your data. Select from CHAID, Exhaustive CHAID, Classification & Regression Trees (C&RT), and QUEST Model evaluation graphs: Use lift, gains, and other evaluation graphs to spot at which point the model offers optimal results Scalable algorithms: As data get larger, you can solve enterprise-sized problems more efficiently ■ ■ ■ Analyze your data with AnswerTree to: Develop better-targeted direct mail programs Offer specific products to the customer groups most likely to purchase them Create campaigns that increase customer retention Product specifications ■ Key features ■ Display tree diagram, tree map, bar graphs, and data ■ Build trees easily with a wizard that prompts you through 44 ■ model-building steps Choose from three tree-generating methods: Automatic, interactive, or production mode View nodes using one of several ways: Show bar charts of your target variables, tables, or both in each node 1.800.253.2575 (U.S. only) Order now! Improve credit scoring Improve student retention and graduation rates Develop more effective government programs and services ■ ■ ■ ■ Collapse and expand branches without deleting the model View and print trees horizontally or vertically Print large trees more easily using the print preview Re-run tree building using production mode; generate scripts Bowman needed a powerful software tool to perform sophisticated analyses of test scores for more than 15,000 students. “We wanted to make decisions based on an analytical appraisal of data,” explains Bowman. “SPSS for Windows and AnswerTree put us in a position to get information that we never had before using student scores from an annual assessment test.” The tests are given each spring and the board typically has only a few weeks to analyze and digest the data before they plan summer school programs. “AnswerTree can quickly point out which factors influenced the target variables so that we can be as productive as possible in a short time,” says Bowman. With the advanced analysis techniques in AnswerTree, Bowman dissected the data in new ways—finding interesting, previously undiscovered relationships among scores in various sections of the test. With the modeling power of AnswerTree, Bowman highlighted the pertinent issues so that everyone— from the school board to the principals to the teachers—could interact with the results. “Ultimately, it gave us a way to take our ever-shrinking dollars and put them where they will do a lot of good,” he explains. “For the first time, principals and teachers had a distinct set of rules to apply toward student achievement. I would never have been able to do such sophisticated analysis without AnswerTree.” Because of the revelations he uncovered, teachers had the time to develop lesson plans to strengthen specific student skills, which should improve the students’ overall scores. automatically from the user interface or edit models directly from the script Algorithms ■ Four powerful decision tree algorithms: – CHAID by Kass (1980) – Exhaustive CHAID by Biggs, de Ville and Suen (1991) – Classification & Regression Trees (C&RT) by Breiman, Friedman, Olshen and Stone (1984) – QUEST by Loh and Shih (1997) Evaluation ■ Interactive evaluation graphs enable visual representation ■ ■ of gains summary table: Gains, response, lift (index), profit and ROI Misclassification chart: Describes model performance, accuracy versus actual and risk estimates Gains chart: Identify segments by highest (and lowest) contribution and select nodes using this criteria For more details and complete specifications, go to www.spss.com/answertree Take your analysis and modeling to a new level AnswerTree takes the output from SPSS (and database files) and with a few mouse clicks and a wizard-based interface, creates decision trees. 1 Save time with easy data access 2 Build better models, faster, with many options 3 Easily spot important segments and factors Put the model to work for you AnswerTree’s easy-to-use interface allows you to adjust your model to your specific situation. Get reliable results quickly by training your model on a subset of your data and then testing the reliability on the remaining portion. Use your models to batch score other data for your desired segments and focus your efforts on the best targets. Act on results quickly Find the ideal cut-off point for your marketing campaign using AnswerTree’s evaluation graphs (including gains, response, lift, profit, and ROI charts). These charts provide value summaries of each segment and a clear picture of your results so you can act on your analysis quickly. Quickly access data from popular database sources using AnswerTree’s ODBC Wizard. You can also import data directly as SPSS Excel and ASCII files. 4 Fine-tune models AnswerTree gives you three ways to build models, including an intuitive Setup Wizard. 5 AnswerTree’s tree diagrams, tables, and graphs are easy to interpret. Use the trees to discover relationships that are currently hidden within your data. Make confident decisions using sound results 6 Put your results to work Instill confidence in your analysis using AnswerTree’s Gain Summary, or its Misclassification chart, which provide a clear report of your model’s accuracy and estimated error. Enhance your model by training it on a subset of your data, then testing its reliability on the remaining portion. Summary report: Document analysis results as well as the criteria used to build trees Deployment ■ Export: – Trees as Windows bitmap (BMP) or meta files – Gains charts and risk summary ■ ■ tables as tab-delimited text files – Rules and summaries as text files – Trees, gains charts and risk, rule and summary tables as HTML Export decision rules that define selected segments in SQL to score databases or SPSS syntax to score SPSS files ■ ■ ■ Export XML models to score cases using models developed in AnswerTree or other systems Import data from SPSS, Excel, and text (ASCII) files Get native access to database management systems including Oracle, SQL Server, DB2; additional For more details and complete specifications, go to www.spss.com/answertree AnswerTree results are reusable and easy to work with. Simply save them as SPSS syntax or SQL, and conveniently use them to score your database or extract records. access to any ODBC-compliant sources using the ODBC Wizard System requirements ■ Operating system: Windows 98, 2000 or Windows NT 4.0 with Service Pack 5 or higher ■ Hardware: Pentium or Pentium class processor, SVGA monitor, and ■ ■ ■ CD-ROM drive for installation Minimum free drive space: 70MB for software Minimum RAM: 64MB Microsoft Internet Explorer 5.0 or later for reading help documents 1.800.253.2575 (U.S. only) Order now! 45 The how’s and why’s of survey research: getting the most value through an effective survey research process SPSS Data Entry 4.0 ■ ■ ■ Quickly design paper-based surveys and desktop data entry forms Eliminate the need to clean and prepare data for analysis Directly compatible with SPSS analytical software Your complete system for collecting and managing survey research data SPSS Data Entry products work together to provide an integrated system for collecting and managing survey research data. Reap the rewards of flexible, professional-looking survey design, and efficient on-screen entry forms. Plus gain powerful data collection and cleaning capabilities—and have data that’s ready for immediate analysis in SPSS. All SPSS Data Entry products offer complete integration with SPSS for Windows, so you can move from data collection to analysis in a single step. Enhance your survey research process with SPSS Data Entry Spell check feature: Enable survey designers to check for spelling errors in design mode, eliminating the need to redo work after errors are discovered in published surveys 64-byte variable names: Create variable names of up to 64 bytes for more specific, descriptive names 4,000-character open response: Enable almost any size text response—up to 4,000 bytes for complete, detailed information Question Library: Choose sample questions with responses and variable definition, and add new questions SPSS (* .SAV) data file: Automatically create SPSS .sav files (with defined dictionaries) as you build your survey forms Product specifications Status bar Auto-backup, auto-save Form creation ■ Drag-and-drop form design ■ Toolbox with many response options: – Text box for long open responses – Option button to select one from ■ ■ ■ ■ ■ Context-sensitive help, how-to’s, and tips Online tutorials Open multiple surveys or forms at once 46 1.800.253.2575 (U.S. only) Order now! a list of choices – Check box to select all that apply (multiple response) – List boxes to easily present a list of options – Drop-down lists to save space – Combo boxes give space for customized responses (e.g., “Other”) ■ – Matrix to organize similar-style questions in a grid Define data file and SPSS dictionary as you build the form – Define value labels from response text – Define variable labels from question text (Excerpt from Step 1: Planning and survey design) Write the questions The key to a successful survey is to ensure that your questions are concise and easy-to-understand. This way, you will get valid and reliable information. No matter how well other features of the survey are designed and executed, poor questions will reduce the value of the data gathered. Use well-written and tested pre-existing questions as much as possible, especially from surveys done in your specific industry or topic area. You can find well-written questions in question libraries. Some software programs have question libraries built in, which can help guide you through professionally written questions. Keep in mind that no question is usable in every situation—so you have to examine the questions for your particular survey research. Pretesting questions is the best method to determine whether a question is correct for your own survey. If you are going to write questions on your own, you might consider taking a training course to learn proven methods for question writing. Design the questionnaire A poorly formatted survey can deter people from responding to your survey. It can also give skewed results. There are two key goals to keep in mind when designing a questionnaire: minimizing measurement error and reducing non-response. Your questionnaire should be constructed so that: ■ Respondents are motivated to complete it ■ The questions are all read correctly and thoroughly ■ Respondents understand how to respond to each question or how to skip, with clear instructions throughout the document ■ Returning the questionnaire is an easy and straightforward task ■ ■ – Set missing values – Define multiple response sets – Enable definition of variable types – Long variable names permitted Copy and paste variable properties Drag-and-drop variables to automatically create questions ■ ■ ■ ■ ■ ■ Question Library of over 300 sample questions and responses Automatic question renumbering Spell-checker to catch errors Customizable design with images Annotation text for headings, instructions, or comments Flexible formatting capabilities For more details and complete specifications, go to www.spss.com/data_entry SPSS Data Entry in the survey research process Make data collection easier than ever before. Here are several capabilities that increase the convenience and effectiveness of your survey research process… Plan and write your survey in no time 1 2 Define your variables accurately 4 6 3 5 After you design your survey 4 define the data rules 5 and SPSS Data Entry Builder ensures you collect accurate data 6 . Begin with speedy form design 1 using preformatted questions 2 from Data Entry Builder’s Question Library—choose from more than 300 questions. Or create your own. 3 Enable openended responses up to 4,000 characters. Plus, spell check is available in design mode. 7 Collect your data in less time 8 Analyze your data With Data Entry Station, collect cleaner, more accurate data in less time—data entry staff and respondents are guided through relevant questions. ■ ■ ■ ■ Property Inspector to control the look of every element of your form, including colors, fonts, size, and borders Efficient entry screens Produce printed surveys Multiple form support in one file Data collection ■ Skip-and-fill rules guide entry ■ Smart navigation features ■ Auto-jump automatically skips to the next field after the maximum number of characters is entered ■ Go to next case, go to case ■ Find and replace Data entry verification ■ Powerful data cleaning rules – Validation rules, checking rules, and skip-and-fill rules ■ Flexible cleaning methods ■ Interactive rules checking ■ Batch mode rules checking ■ Compare versions verification For more details and complete specifications, go to www.spss.com/data_entry Once your data is collected, it’s immediately ready for analysis using SPSS. ■ ■ ■ ■ ■ Checking report by case or rules Rules Wizard for step-by-step rules setup Rules editor with scripting for advanced and customized rules Copy rules between surveys Standard or custom alerts System requirements (SPSS Data Entry Builder only) ■ Pentium® processor or higher ■ Microsoft Windows 98, 2000, Me, or Windows NT 4.0 ■ 16MB RAM; more for large surveys ■ 75MB hard drive space 1.800.253.2575 (U.S. only) Order now! 47 Political campaigns depend on accurate sample sizes—do you? SamplePower 2.0 ■ ■ ■ “I cannot believe the time SamplePower saves and how easy it is to use.” – Mandel Bellmore, Ph.D., President, Block, McGibony, Bellmore & Assoc., Health and Hospital Consultants Determine sample size with ease Test results before beginning Explore and tailor research parameters A campaign manager wishes to conduct a tracking poll. With a $50,000 budget, she can conduct interviews at an average cost of $50 per interview. What sample size should she use in order to have adequate statistical power, get a statistically significant result, and stay within her budget? Save time, effort, and money by identifying the sample size you need SamplePower easily arrives at the sample size required. The campaign manager selects a test that will give her a 10-point spread. She sets up her parameters and explores the relationship of power and sample size given the other specifications. Running SamplePower, she discovers that an overall sample size of approximately 800 will give her the desired statistical power. SamplePower is the front end of a complete line of research and analysis software from SPSS. Whether you’re an advanced or beginning statistician or researcher, you’ll easily identify the appropriate sample size—every time—for any research criteria. Strike the right balance among confidence level, statistical power, effect size, and sample size using SamplePower. SamplePower uncovered: ■ The poll costs only $40,000, so she saves 20% of her budget ■ She saves the time it would take to conduct the extra 200 interviews ■ She saves the effort it would take to enter extra data collected in the interviews Four reasons why SamplePower is the #1 choice for researchers: 1. Save time, effort, and money: It’s crucial to have an accurate sample size to prevent: A missed research finding, when your sample size is too small Wasted time and resources, when your sample size is too large 2. Present your results clearly: Deliver impressive reports with the Report tool Product specifications Create scenario text reports Find N for any power ■ Show Cohen’s effect size conventions for specific tests Working with results ■ Pivot tables ■ New export and print options, including export to Excel ■ Display multiple graphs to quickly assess the impact of various factors either alone or in conjunction ■ Graphs linked to pivot tables and to reflect the structure of the tables ■ ■ General features ■ Set Alpha level; 1 or 2 tailed tests; number of decimals displayed; N of cases for min, max, and increment; computational formula (some exact formulas implemented); data entry; and study design options ■ Show power and precision (depends on test) with varied sample sizes, power only, or with varied effect sizes and Alphas 48 1.800.253.2575 (U.S. only) Order now! 3. Simple to learn and use: Interactive guides help you determine an effective sample size 4. Covers the statistics you need: Access powerful statistical techniques such as means and their differences, ANOVA, regression, and more Export graphs as WMF, EMF, BMP, and Word or PowerPoint Statistical tests Means ■ One-sample and paired t tests when mean equals zero or equals a specified value ■ Precision ■ t test for two independent groups with variance known and unknown Proportions ■ One-sample test that proportion = 0.50 or specific value ■ Without SamplePower, the campaign manager might have spent her entire budget, created unnecessary work, and arrived at her result later than she did. 2x2 for independent samples 2x2 for paired samples (McNemar) ■ Sign test ■ KxC for independent samples Correlations ■ One-sample tests that correlation = zero or specific value ■ Two-sample test that correlations are equal: Computational option for power and Fisher Z transformation ANOVA ■ Oneway Analysis of Variance and Analysis of Covariance ■ ■ Factorial Analysis of Variance and Analysis of Covariance: Two factors and three factors Regression ■ Templates for study design ■ Error model Logistic regression ■ One continuous predictor or two continuous predictors ■ One categorical predictor with two or more levels Survival analysis ■ Accrual options: Subjects entered prior to first study interval, subjects ■ entered during study at constant rate, and accrual varies ■ Hazard rate options: Constant and varies ■ Attrition rate options: No attrition, constant rate, and rate varies Equivalence tests ■ Equivalence tests for means and for proportions System requirements ■ Pentium-class processor; Microsoft Windows 95, 98, 2000, or Windows NT 4.0 For more details and complete specifications, go to www.spss.com/samplepower Get precise results faster with flexible, efficient tools SamplePower is packed with features that make finding accurate sample sizes easy. Convenience is built in at every level, from the smooth user interface to behind-the scenes statistical computations that give results in seconds. You get the clear, precise answers you need to move forward with your research. 3 1 2 Perform analysis in minutes Make informed decisions at every step Once you’ve found a sample size, the most important thing is being able to share your results with clients or colleagues. SamplePower gives you three fast and easy ways to share results. 1. Report tool communicates your results clearly SamplePower’s interactive summary panel gives you concise summaries of power and precision at any point, so you can see how each decision affects your results. SamplePower’s interactive guide leads you smoothly through your analysis. The guide explains terms and takes you through the steps necessary to determine an effective sample size. Compare results before you begin your research 4 See how your research criteria will affect power Get accurate guidance with Cohen’s effect sizes SamplePower’s Tool menu provides Cohen’s effect size conventions, which allow you to determine effect sizes for particular tests by simply clicking on an icon. Cohen’s effect size provides users with a “rule-of-thumb” for determining otherwise ambiguous “small,” “medium,” and “large” effect sizes. Plug these effect sizes into the main screen to see how varying the effect size affects power or precision. SamplePower’s tables and graphs allow you to easily assess how different combinations of your research parameters (such as proposed sample size, Alpha levels, and duration) affect your statistical power. 6 Simply use the Report tool and a complete report is displayed on the screen. You have the flexibility to embed the report in a word processor document and to create convincing proposals. 2. Support your results with embedded tables The Table tool gives you a table showing power and precision at select sample sizes. Easily view how sample size affects power or precision. Plus, you can embed this table in a word processor for informative presentations. The Stored Scenarios tool gives you optimum control over the flow of your research. You can vary Alpha level, power, effect size, or sample size in the main screen and store your results as you continue. This illustration shows how the sample size varies as other settings, such as Alpha, are changed. 5 Present your results clearly 3. Enhance the understanding of your research with graphics Find sample sizes in one click For more details and complete specifications, go to www.spss.com/samplepower SamplePower’s Find N tool finds the sample size for the default power setting in one click. You also have the flexibility to choose different power-size settings to compare results. The Graph tool generates graphs relating power to sample size. Graphs provide a visual aid that help determine how sample size affects power. Even include charts in documents. 1.800.253.2575 (U.S. only) Order now! 49 You can be an SPSS star... and receive a free gift. We need your story about how you use SPSS products We’re looking for stories about how SPSS users put SPSS software to work for themselves and their organizations. Tell us how SPSS add-on modules (SPSS Regression, SPSS Conjoint, SPSS Tables, etc.)—or other SPSS products like Amos, SamplePower, or SmartViewer Web Server—have helped you get through a tough assignment. Submit your story of any length—even a few sentences will do—and it might be published in an upcoming product guide (with your permission, of course). If we use your story, you’ll receive a FREE SPSS prediction orb. Offer ends December 29, 2006, and is limited to the first 250 qualified entries. Go to www.spss.com/story to submit your SPSS story. Here are a few “starters” to help you tell your story: ■ My organization benefits from using (SPSS product) because... ■ I doubt if I would have discovered __________ from my data if I hadn’t used (SPSS product)... ■ My colleagues were amazed when I was able to do __________ by using (SPSS product)... ■ Most people don’t know that by using (SPSS product), you can __________ ... ■ If someone took (SPSS product) away, it would mean... ■ My favorite tip or trick with (SPSS product) is... ■ (SPSS product) saves me time by... If we use your story, not only will you be an instant star, but you’ll also receive a FREE SPSS prediction orb. Maybe you owned a prediction “8-ball” during your childhood. The SPSS Prediction Orb provides you with “statistically correct” answers–just ask the orb a question, then flip the ball over to receive answers such as “No correlation,” “Beware the outliers,” or even, “You got a raw score.” University of Chicago Hospitals increase patient satisfaction with Web reporting SmartViewer Web Server 5.0 ■ ■ ■ Easily share and review analytical reports in a Web environment Interact with reports to immediately get the answers you need Make more informed, timely decisions Deploy SPSS results with interactive Web reporting For more information, or to place an order, please call 1.800.253.2575 Start making better decisions by sharing strategic information using SmartViewer Web Server, the analytical content portal for SPSS products. Analysts publish reports from SPSS for Windows or Mac to SmartViewer Web Server’s secure database. No special downloads or installations are required for information consumers to view the reports using a standard Web browser. SmartViewer Web Server centrally stores all of your organization’s analysis, including pivot tables, graphs, charts, OLAP reports, and HTML content and output from third-party products such as Microsoft Office. Instant results with Web-based analytical reports SmartViewer Web Server eliminates the frustrations of static, paper-based reports because it empowers you to: ■ Organize your reports within a convenient home page which includes customizable categories that enable you to find what you need right away ■ Eliminate the need for someone to create new reports when you want different views of the information. SmartViewer Web Server’s interactive tables enable you to pivot rows, columns, or layers, and drill down to see the results in more meaningful ways. U .S. News & World Report recognizes the University of Chicago Hospitals & Health System (UCHHS) every year as one of “the nation’s best hospitals.” UCHHS maintains this title by realizing the need for measuring patients’ feedback and making continuous improvements that address their concerns– based on more than 45,000 patient visits and 2,500 admissions each month. To ensure patient satisfaction, Kim Carli, patient satisfaction measurement project manager at UCHHS, conducts continuous surveys on every facet of patients’ hospital stay, from the courtesy and knowledge of hospital staff to bathroom cleanliness. After analyzing responses, she produces reports that provide hospital managers a way to measure their performance in areas where they can improve the quality of a patient’s stay, such as courtesy and wait time. When Carli first joined UCHHS, writing, formatting, and delivering these reports took up to three weeks per month. Not only did this delay reports from reaching hospital managers promptly, it also prevented her from devoting the necessary time to improve patient satisfaction. Carli wanted to reduce the frustration and time of processing reports by switching to an electronic-based delivery system. With SPSS Inc.’s SmartViewer Web Server, she discovered a solution that allowed her to customize, automatically publish, and rapidly distribute reports via the Web. As a result, the UCHHS: ■ Reduced report processing time from three weeks to one week and freed up resources to improve patient satisfaction ■ Quadrupled the output of reports from 10 to 40 per month ■ Promoted a shift to “paperless” reporting with the aim of making it part of the hospital’s intranet strategy First, the analyst publishes a report using SPSS. Recipients then access SmartViewer Web Server to view and interact with the results in their Web browsers to view the information most relevant to them. For more details and complete specifications, go to www.spss.com/smartviewer_server 1.800.253.2575 (U.S. only) Order now! 51 Clementine Desktop ■ ■ ■ Quickly add the power of data mining to your analysis Keep the convenience and cost-effectiveness of working from your desktop Take advantage of an intuitive graphical interface to visualize every data mining step Quickly add the power of data mining to your analysis Data mining enables you to generate new hypotheses from data. Users of SPSS statistical tools have the algorithms, computer power, and statistical expertise to dig deeply into a large amount of data; many also look to data mining for an even broader analysis. Data mining uncovers previously unknown patterns and connections in data, enabling you to improve business processes and make the right decisions at the right time. SPSS offers Clementine Desktop to enable you to realize the benefits of data mining for smaller problems where the power of server software and enterprise integration is not required. Clementine Desktop can be installed quickly on a personal computer—so you can begin mining your data right away. These products are designed with business users in mind, so you don’t need to be an expert in data mining to enjoy its benefits. Clementine is SPSS’ industry-leading data mining solution With Clementine Desktop, your business knowledge guides the process Statistical analysis tests hypotheses, one at a time. Data mining generates its own hypotheses automatically—often many at one time. Like a satellite deployed over your organization’s world of complex data, Clementine uses techniques including rule induction and neural networks to reveal patterns that were previously hidden in masses of data. You can combine the data mining power of Clementine with the statistical might of SPSS to gain new insights into some of your organization’s toughest issues. The product’s intuitive graphical interface makes it easy to visualize every step of the data mining process. You don’t need to write code; instead, you can focus on knowledge discovery and pursue “train-of-thought” analysis. This leads to data mining productivity—a faster achievement of your business goals and a quicker “timeto-value.” Clementine Desktop can also be enhanced with a Text Mining module, so you can extend your analysis to unstructured data. Customer scenario: how Clementine and SPSS work together for in-depth analysis A cell phone service provider uses Clementine’s data mining ability to discover which customers are most likely to switch to another provider. The analysis identifies that males age 30-40 with a particular model handset are 50 percent likely to churn. This is a totally new insight that contradicts the company’s previous “conventional wisdom.” To ensure that a Clementine model has truly identified something new, company analysts often run a number of statistical analyses using SPSS. They measure the statistical significance of the discovered pattern and perform a “survival analysis” to help understand the length of customer relationships (before they churn). These procedures give the company additional confidence that they are committing their resources wisely to address this churn profile identified by Clementine. Finally, the company uses SPSS to create charts and graphs that are placed in a Word document report summary that provides recommendations to decision makers. Clementine allows you to visualize the complete data mining process. Clementine Desktop is a component of the larger Clementine family of products. To learn more about how you can economically add data mining to your organization’s arsenal of data analysis, contact an SPSS representative at 1.800.253.2575 (U.S. only). Or visit www.spss.com/clementine. 52 1.800.253.2575 (U.S. only) Order now! For more details and complete specifications, go to www.spss.com/clementine mrInterview 3.5 and mrTables 3.5 The perfect survey solution for organizations looking for: A data collection platform that is fully integrated with SPSS for Windows Software that can grow as needs progress Secure, online access for users A way to streamline their research processes The ability to conduct research in any language Centralize survey data collection and analysis ■ Create visually appealing surveys through Web, phone, paper, and handheld devices ■ Create tables that analysts can immediately interact with online ■ “As our primary data collection engine for online interviewing, Create and conduct surveys with confidence using mrInterview mrInterview enables us to deploy sophisticated surveys online. The depth of mrInterview’s features, including sample management and quota control, coupled with its customization options, makes it an ideal addition to our research infrastructure.” – Michael Reuscher, Vice President, IT project management, Synovate mrInterview is a complete solution for fielding and managing large or small Web projects with maximum efficiency—all without sacrificing the sophistication that professional researchers rely on. It includes the security, access, permissions, and features you need to easily create and administer surveys and report on data through a Web browser. You can adapt mrInterview to your employees’ experience level—from beginner to expert—enabling them to create simple or complex surveys. Whether your organization runs a few surveys per year or has extensive data collection operations, mrInterview adapts to fit your needs. Easy to use Through mrInterview, you can ensure security by assigning permissions for a variety of users. Permission levels range from full access for individuals, such as your survey creators, to view-only access With mrInterview, you can easily set up and run projects, moving smoothly from authoring to activation and testing, and then to the analysis and exporting of data. Secure deployment Share survey research tables online with mrTables Trends, opinions, and attitudes are constantly changing. To keep colleagues and clients up to date on the most recent findings, you need an efficient way to share your results. mrTables enables you to share your research tabulation results online with anyone, anywhere, via your Web browser. Present results to clients in another department, office, city, or country. Create tables that analysts can immediately interact with online. Use data in different formats—and even different languages—without changing the user environment. Even publish your survey reports to Microsoft Excel and other popular reporting applications. For more details and complete specifications, go to www.spss.com/dimensions of results for your clients. Everyone gains access through a common interface—and you control who sees what, based on permissions you set. To keep your Web-accessible content secure, you can keep your response data on a separate machine, behind a firewall. You can also easily add specialized, thirdparty security systems to mrInterview. mrInterview and mrTables are part of the SPSS Dimensions survey research platform All Dimensions products are designed to work with each other for seamless survey research. The Dimensions line enables organizations to control and optimize the entire process of collecting, analyzing, and managing customer data. For more information visit www.spss.com/Dimensions. 1.800.253.2575 (U.S. only) Order now! 53 SPSS Tip Using the REPLACE function with SPSS to clean up data sets Clean up your datasets with the REPLACE function Figure 1: There are several strings of characters that need to be replaced The REPLACE function in SPSS 15.0 makes it easy to clean up your dataset. Now you can replace one string character with another. The REPLACE function allows you to remove spaces and characters, replace one word with another—and much more. Clean your dataset up in no time at all. Example 1: To remove the spaces between the values in variable “id” and remove the quote marks under “responses,” replace these characters with null values. (Figures 1-2) COMPUTE id = REPLACE(id,” “, “”). EXECUTE. Figure 2: You’ve successfully replaced the spaces between the variables under the variable “id” and removed the quote marks around the characters under “responses.” COMPUTE responses = REPLACE(responses,’”’,””). EXECUTE. To replace capital letters with lowercase letters: (Figure 3) IF (INDEX(responses,’ABODES’))>0 responses=REPLACE(responses,’ABODES’,’abodes’). EXECUTE. Other examples include... To replace a single letter: IF (INDEX(responses,’Abodes’))>0 responses=REPLACE(responses,’A’,’a’). IF (INDEX(responses,’abodeS’))>0 responses=REPLACE(responses,’S’,’s’). EXECUTE. Finally, you can also replace a word with another word: IF (INDEX(responses,’abodes’)) > 0 house=REPLACE(responses,’abodes’,’homes’). EXECUTE. 54 1.800.253.2575 (U.S. only) Order now! Figure 3: The capital letters in the third “responses” line (ABODES) have been replaced with lowercase letters. SPSS In the News Noteworthy headlines and articles Marc Ecko Makes Designs on More SPSS Software for Brand Performance Analysis M arc Ecko Enterprises has purchased additional SPSS predictive analytics technology to help analyze brand performance at a retail level. As Marc Ecko Enterprises has achieved significant success using SPSS to analyze its various apparel brands at a wholesale level, implementing additional SPSS software will enable the global fashion and lifestyle company to gain a new perspective on brand management. The company, that reported international retail sales of approximately $1.2 billion in 2005, purchased more SPSS software so it could achieve a complete view of key business metrics and customer trends. Worldwide, 16 of the top 20 retailers use SPSS software. “SPSS has become critical to all aspects of our company, from the design of our various lines to the way our sales team goes to market,” said Mark Faber, senior vice president of Business Solutions, Marc Ecko Enterprises. “With SPSS, we’re able to identify key growth areas and gain a competitive edge with our customers.” Brand names under Marc Ecko Enterprises include ecko unltd., the world famous rhino brand; Marc Ecko “Cut & Sew,” a contemporary menswear line launched Fall 2004; G-Unit® clothing and accessories, a joint venture with multi-platinum musician, 50 Cent; Zoo York®, a line of action sports-inspired clothing and accessories; and Avirex, a recently acquired mid-tier sportswear collection. SPSS Software Helping to “Mushroom” Business for International Produce Company Continued from page 5 “With this software, employees are spending a lot less time waiting for reports and gathering information, and more time analyzing the business and making the necessary changes to meet their business goals,” said Burnham. Monterey Mushrooms president and chief executive officer Shah Kazemi is so pleased with SPSS software that he has had it implemented for all senior-level personnel to help them better understand their revenues and margins. SPSS software lets executives view and interact with customized reports— which are all based on the same information—to help them make the right decisions quickly. “Because of SPSS, we’re able to see our data as we’ve never seen it before,” added Burnham. “We’re able to view it from different angles and perspectives. That allows us to better analyze our margin of profitability and highlight exceptions quickly, which, in turn, allows us to make better business decisions.” www.spss.com 1.800.253.2575 (U.S. only) Order now! 55 er t s i g Re ! y a d to SPSS Directions Nov. 5-9 North American User Conference Th e F a i r m ont C h i c a go , C h ic a g o, Il lin ois Join us at the SPSS Directions North American User Conference and: ■ ■ ■ ■ ■ ■ ■ ■ ■ Attend fascinating and relevant keynote presentations Enjoy educational break-out sessions Expand your knowledge with pre- and post-conference training courses Network with colleagues and SPSS experts Preview new and emerging technologies See software demonstrations at the SPSS Demo Center Visit the SPSS Expo Center to see new trends in analytical software Learn tips, tricks, and techniques to master your SPSS software Tour SPSS world headquarters (limited availability–register early) 2006 Keyno te Spea ker Steven D. Levitt – Bestselling Author, FREAKONOMICS – FREAKONOMICS has been on The New York Times Bestseller List for over a year Register today: www.spssdirections.com $3.95 Printed in the U.S.A. © 2006 SPSS Inc. All rights reserved. SCATV10-0806