EDRE6654 - MULTIVARIATE STATISTICS FOR APPLICATIONS TO EDUCATIONAL PROBLEMS
Gabriella Belli, Ph.D.
office: 703.538.8477
home: 301.951.5291
e-mail: gbelli@vt.edu
Office: Room#438
CATALOGUE DESCRIPTION
Multivariate statistical procedures presented in an applied research setting. Oriented toward the logical extension of univariate tests of significance and estimation procedures to multivariate problems. Emphasis is on understanding the techniques and their use via discussions of empirical research articles, plus consideration of outputs using existing computer software packages.
Grimm, L.G. and Yarnold, P.R. (eds.) (1995) Reading and Understanding Multivariate Statistics. Washington, D.C.: The American Psychological Association.
Recommended, but not required
Grimm, L.G. and Yarnold, P.R. (eds.) (2000) Reading and Understanding MORE Multivariate Statistics. Washington, D.C.: The American Psychological Association.
(May be ordered from APA, 1-800-374-2721 or 202-336-5510)
Students may choose any statistical software package, but most class examples will be demonstrated using SPSS or JMP. Both SPSS and LISREL outputs are provided in the textbook.
Course documents will be available for printing from Blackboard (log onto www.learn.vt.edu using your VT PID). If you do not use your VT email, PLEASE MODIFY IT SO THAT ANY MESSAGES WILL REDIRECT TO YOUR PERSONAL EMAIL.
ORGANIZATION OF COURSE
1) Brief introduction to the analysis and its use via applications (through both text examples and articles). This will depend heavily on class discussions.
2) Further explanation of theory and logic of the analysis via lecture and a review of outputs.
We will also review some fundamentals of univariate statistics (as needed), review data screening procedures, and end with an overview of some additional multivariate procedures. Nothing more than a background in basic algebra will be expected. In keeping with the notion of continuous quality improvement, modifications may be made depending on student input.
ASSIGNMENTS
Grades will be based on two exams and one paper. Text chapters and research articles will be the basis for class discussion. These must be read prior to class.
1. Data analysis (using multivariate statistics) of an appropriate data set and a report of the results. The report would include appropriate presentation of tables and discussion (similar to what would be included in a Chapter 4 of the dissertation), as well as a thorough discussion of why the analysis selected was the appropriate one (as might be found in a Chapter 3).
2. A critique of an empirical study where the analysis was multivariate in nature. Report would describe what was done and why it was appropriate to the research questions addressed, as well as provide suggestions for alternative analysis strategies.
3. Select one multivariate technique and write a paper explaining its purpose, how it used, problems with using it, etc. Basically, a paper that shows that you understand the technique and how to use it.
4. Summary of multivariate statistical procedures as used in published empirical research studies in your field. This would include information about samples, methods, effect size, assumptions, etc.
BASIC TOPICS COVERED
multiple regression, canonical correlation, path analysis principal components, factor analysis
discriminant function analysis, logistic regression, multivariate analysis of variance meta analysis – not a multivariate method, but a way to statistically summarize published results Additional techniques may be covered as needed
ADDITIONAL REFERENCES - Multivariate Texts:
Bock, R.D. (1985) Multivariate Statistical Methods in Behavioral Research. Scientific Software Inc. Dunteman, G.H. (1984) Introduction to Multivariate Analysis. Beverly Hills, CA: Sage Publications. Hair, J.F., Black, W.C., Babin, B.J., Anderson, R.E., & Tatham, R.L. (2006). Multivariate Data Analysis
(6th ed.). Upper Saddle River, NJ: Pearson Prentice Hall.
Manly, B.F.J. (1994) Multivariate Statistical Methods: A Primer (2nd ed.) NY: Chapman & Hall USA. Morrison, D.F. (1990) Multivariate Statistical Methods (3rd ed.) NY: McGraw-Hill Publishing Company. Sharma, S. (1996) Applied Multivariate Techniques. NY: John Wiley & Sons, Inc.
Stevens, J. (1986) Applied Multivariate Statistics for the Social Sciences. Hillsdale, NJ: Lawrence Erlbaum Associates.
Tabachnick, B.G., and Fidell, L.S. (1989) Using Multivariate Statistics (2nd ed.). NY: Harper Collins.
*** This was used as the textbook for this class in the past. It provides input and output for SPSS, SAS, and BMDP on the mainframe and for SYSTAT on the PC.
*** Ten raw data files and the front end of SPSS program files (both in ASCII format) are provided.
Tatsuoka, M.M. (1988) Multivariate Analysis (2nd ed.) NY: Macmillan Publishing Company.
Tacq, J. (1997) Multivariate Analysis Techniques in Social Science Research: From Problem to Analysis. London: Sage Publications.
*** Used as a text in the past. It approaches the subject from a research question perspective. Timm, N.H. (1975) Multivariate Analysis with Applications in Education and Psychology. Monterey, CA:
Brooks/Cole Publishing Company.
MULTIVARIATE STATISTICS - Tentative Schedule
Published by admin on September 26 of 2008
