Download The Statistics Department at George Washington University will

The Statistics Department at George Washington University will offer the
following Graduate Course in Spring 2003 (January 13 – May 13, 2003)
Enhance your statistical analysis skills by taking one or more of these
courses. Registering as a non-degree student is easy – visit
www.gwu.edu/~regweb/ for detailed instructions.
For questions or further information please contact Dr. Tapan Nayak, e-mail:
[email protected], ph: 202-994-6888.
Stat 202: Mathematical Statistics. Thursdays, 6:10pm-8:40pm.
Instructor: Dr. Kaushik Ghosh
This is the second part of a two-part series in Mathematical Statistics. The objective is to
familiarize students with the concepts of Mathematical Statistics at the graduate level.
The course is required for MS and Ph.D. students in Statistics, and Biostatistics, and
Ph.D. students in Epidemiology. Graduate students from other quantitative fields such as
Economics, Finance, and Engineering would also find this course useful.
Prerequisite: Multivariable Calculus (Math 33), Linear Algebra (Math 124), and Stat 201
or equivalent.
Stat 202 deals mostly with the statistical inference (201 deals with probability theory).
Topics to be covered include sampling distributions, Central Limit Theorem, data
reduction principles (sufficiency, ancillarity, and completeness), point estimation
(method of moments, maximum likelihood, and Bayes estimation), properties of point
estimators (unbiasedness, minimum variance, efficiency, Cramer-Rao inequality),
hypotheses testing (likelihood ratio and Bayesian tests, Neyman Pearson Lemma, power
and size of a test, p-value), interval estimation (Bayesian HPD intervals, intervals
obtained through inversion of a test statistic or from a pivotal quantity) and asymptotic
properties of procedures (consistency and efficiency of estimators, large-sample
confidence intervals, asymptotic distribution of likelihood ratio tests). This is roughly
chapters 5-10 of the text: Statistical Inference by Casella and Berger (2nd ed.).
Stat 210: Data Analysis. Mondays, 6:10pm-8:40pm.
Instructor: Dr. John Lachin
Review of statistical principles of data analysis, using computerized statistical analysis
procedures. Multiple regression and the general linear model, analysis of contingency
tables and categorical data, logistic regression for qualitative responses, analysis of
variance and covariance. Statistical analysis and interpretation of results. Complete
syllabus at http://www.bsc.gwu.edu/~jml/class/stat210/syllab00.pdf. Prerequisites: Stat
118, Stat 157 or 201, and Stat 183 or equivalent.
Stat 213: Intermediate Probability & Stochastic Processes. Wed., 6:10-8:40 pm.
Instructor: Dr. Zhaohai Li
Topics include: Random variables and their distribution; Conditional distribution and
conditional expectation; Convergence of random variables: almost surely, in probability,
in rth mean, in distribution; Probability inequalities: Markov inequality, CauchySchwartz inequality, Jensen's inequality; Branching process, Poisson process, Brownian
motion, martingale theory. Prerequisites: Stat 201-2 or equivalent.
Textbook: Probability and Random Processes by G. R. Grimmett and
D. R. Strizaker.
Stat 216: Applied Multivariate Analysis 2. Wednesdays, 6:10pm-8:40pm.
Instructor: Dr. Reza Modarres
This is the second part of a two-semester sequence in Applied Multivariate Analysis. The
course is designed to introduce students to statistical analyses of several variables, most
likely dependent, following a joint normal distribution. Topics include, comparisons of
several population means, multivariate linear regression models, principal components,
factor analysis, inference for structured covariance matrices, canonical correlations,
discrimination and classification, clustering and distance methods. Additional topics from
the literature will also be covered. There will be many applications of these multivariate
techniques to analyses of data from the behavioral, social, medical, and physical sciences.
The computational aspects will include use of matrix algebra tools (SAS/IML).
Prerequisites: a course in matrix algebra (Math 124) and mathematical statistics (Stat
157-8). Textbook: Applied Multivariate Analysis, 5th Ed., by R.A. Johnson and D.W.
Wichern.
Statistics 221: Design of Experiments for Behavioral Sciences. Thursdays, 6:10pm8:40pm.
Instructor: Dr. Curtis Tatsuoka
The main objectives of this course are to give students a thorough understanding of
ANOVA, and to discuss in some detail the topic of experimental design. ANOVA and
methods for experimental design involve some of the most important and useful concepts
that are used in statistical practice. While the course is not theoretically-oriented, the
class will give a thorough presentation of ideas and formulas. SAS programming will be
required, as well as a project (to be proposed by the student) that requires analysis of
actual data or the development of an experimental design. Data from dissertation projects
or from work are encouraged. This class should be beneficial not only to students in the
behavioral sciences, but in fields such as medicine, business, and engineering. Having a
background in regression and SAS programming is helpful but not essential.
Topics include multifactor ANOVA, simultaneous inference, diagnostics and remedial
measures for violations of assumptions in ANOVA, random and mixed effects models,
analysis of covariance, randomized block design, nested designs, repeated measure
designs, Latin square designs, fractional factorial designs, response surface methodology.
The text is “Applied Linear Statistical Models” by Neter et. al., 4th edition, McGraw-Hill.
Stat 223: Bayesian Statistics: Theory and Applications. Thurs., 6:10pm-8:40pm.
Instructor: Dr. Sudip Bose
This course will provide an overview of Bayesian theory, methods, and applications,
starting with a discussion of why one would use Bayesian methods. Topics include
foundational issues -- the likelihood principle and the Bayesian approach, conjugate
priors and non-informative priors, Bayesian estimation, Bayesian testing of hypotheses
and the Bayes factor, Bayesian linear models, robustness of Bayesian analyses, and
computational issues. Prerequisite: Stat 201-202.
Stat 258: Distribution Theory. Mondays, 6:10pm-8:40pm.
Instructor: Dr. Joseph L. Gastwirth
The course builds a bridge between probability theory and its application in statistics by
providing the student with a repertoire of techniques of distribution theory that receive
wide applications in statistics. The course is beneficial to students wishing to move on to
the next level of sophistication and mathematical maturity needed for advanced study in
any of the fields of stochastic processes, probability theory, or statistics. Prerequisite:
Master’s level background in probability and statistics. Background in measure-theoretic
probability is helpful but not required.
Topics include: moments and cumulants; characteristic and moment generating functions;
specialized probability inequalities, the empirical distribution Lorenz curve; asymptotic
theory – the delta method, extreme value theory, large deviations; order statistics and
spacing.
Textbooks: Stuart, A. and Ord, K. (1987). Advanced Theory of Statistics, Vol. I
Distribution Theory, Oxford University Press, and David, H. (1981). Order Statistics.
Reference texts: Sarfling, R.J. (1980). Approximation Theorems of Mathematical
Statistics, Wiley, New York. Linear Statistical Inference and Its Applications; Wilks, S.
(1962). Mathematical Statistics. Princeton University Press, Princeton, New Jersey;
Arnold B., Balakrishnan, N., and Nagarajah, H. (1992). A First Course in Order
Statistics. Wiley, New York.
Stat 264: Advanced Statistical Theory 2. Tuesdays, 6:10pm-8:40pm.
Instructor: Dr. Subrata Kundu
This is the second part (along with Stat 263) of a two-semester sequence in advanced
statistical theory. The course covers asymptotic theory, hypothesis testing, and
confidence regions. Useful asymptotic theory for estimation and hypothesis testing is
covered. In addition, one learns the theoretical foundation for the construction of UMP
tests and UMP among unbiased (UMPU) tests, in the exponential family, and in
particular, the normal family and the concepts of similarity and Neyman structure;
confidence sets, uniformly most accurate (UMA) confidence sets and UMA unbiased
confidence sets. Prerequisite: Stat 257, and 263.
Stat 281: Advanced Time Series Analysis. Wednesdays, 6:10-8:40pm.
Instructor: Dr. Nozer D. Singpurwalla
An introduction to the paradigms for forecasting using regression and time series
analyses. The role of conditional expectation and inverse probability as a foundation for
the structure of regression and time series models. Time series as realizations of
stochastic processes such as the autoregressive and the moving average. Techniques of
time series analysis. The structure of dynamic linear models and Kalman filter models
and their role in time series analysis and forecasting. The control of filtered processes via
the principle of maximization of expected utility. Examples, applications and case
studies. Prerequisite: Math 33, Stat 201-2 or equivalent.
Stat 288. Modern Theory of Survey Sampling. Thursdays, 6:10pm-8:40pm.
Instructor: Dr. Promod Chandhok
The main objectives of the course are to provide a rigorous treatment of sampling theory
and its applications. With this background the student can modify the existing theory,
develop new theory, and better understand its applications. The prerequisite for the class
is Statistics 287, or equivalent. Statistics 287 introduces simple random sampling with
and without replacement, systematic sampling, unequal probability sampling with and
without replacement, ratio estimation, difference estimation and regression estimation.
This course will introduce the following areas: sampling and subsampling of clusters;
multistage sampling; double sampling; repetitive surveys; errors of response and
nonresponse and some ways of dealing with them, and; small-area estimation.