Download 3 - Problem Identification and Hypothesis

Zainal A. Hasibuan [email protected]) RESEARCH METHODOLOGY
COMPUTER SCIENCE FACULTY, UNIVERSITY OF
INDONESIA
Session Objec4ves •  To understand the first step of conduc4ng research: state general problem •  To be able to iden4fy specific research problems •  To be able to construct hypothesis or research ques4ons •  To be able to determine research objec4ves Problem Iden4fica4on •  Determine a well define general problem –  Sources: research ar4cles, scien4fic discussion, experience, etc. –  Point of interest: phenomena, theories, previous research results, etc. •  Exercise your thought to express the problems •  Write them as quickly as possible •  Be ready, that some (may be all) of your general problems are not researchable –  Conduct literature search –  Consult experts No Problem No Research Agree? Or Disagree? Problem Formulation
Problem Formulation
Identification Research
Problem
Identification Scope of
Research
1. Statistical Hypothesis
2. Hypothetical Statement
Identification Research
Questions
Identification Research
Objectives
Hypothesis •  Basically, there are to types of hypotheses: –  Hypothe4cal statement –  Sta4s4cal hypothesis •  Hypothe4cal statement does not use sta4s4cal analysis –  Apakah IT dapat meningkatkan kinerja perusahaan? –  Biasanya menggunakan pendekatan kualita4f •  Sta4s4cal hypothesis uses sta4s4cal analysis. –  Menggunakan pendekatan kuan4ta4f. Statistical Hypothesis
 
Two-tail hypothesis: Reject H0 if calculated
value is either smaller than -zα (- tα ) or greater
than zα ( tα )
 
One-tail hypothesis: Reject H0 if calculated
statistics value is greater than zα ( tα )
 
One-tail hypothesis: Reject H0 if calculated
statistics value is smaller than -zα ( -tα )
Statistical Hypothesis Test: Steps
1.State the research hypothesis (“alternate
hypothesis), H1
2. State the null hypothesis, H0
3. Choose an α-level (alpha-level)
Typically .05, sometimes .10 or .01
4. Look up value of test statistic corresponding to the
α-level (called the “critical value”)
 
Example: find the “critical” t-value associated with
α=.05
5.Use sta4s4cs to calculate a relevant test sta4s4c. –  T‐value or Z‐value –  Soon we will learn addi4onal ones 6.Compare test sta4s4c to “cri4cal value” –  If test sta4s4c is greater, we reject H0 –  If it is smaller, we cannot reject H0 Hypothesis Test: Errors •  When we falsely reject H0, it is called a Type I error •  When we falsely fail to reject H0, it is called a Type II error •  In general, we are most concerned about Type I errors… we try to be conserva4ve If I am false,
you are true
H0
If I am false,
you are true
Ha
Taken in Combina4on, There are Four Possibili4es Researcher
H0 is true
H0 is false
Accepts H0
Rejects H0
Correct decision
Type I error
Probability = 1- α
Probability = α
Type II error
Correct decision
Probability = β
Probability = 1- β
Determine Research Objec4ves •  Make sure you have a strong reason why such research is worth of doing –  Study the impact? –  Study the usage? –  Etc. •  Research objec4ve should reflect the solu4on of the problem –  If you can not state the problem, you can not state the objec4ve •  Build your reasons based on facts (previous studies, exis4ng problems, etc.) •  (See slide: the aims of research) •  Write several general problems related to CS and IT. •  Build argument why such general problems are worth to research. •  Express your experience in sta4ng hypothesis –  Hypothe4cal statement –  Sta4s4cal hypothesis