*520T - Factor Analysis

SYLLABUS - Click here

Week 1 Readings:

-- Introduction to EFA

Chapter 1 - Gorsuch

1A - Vincent, D.F. (1953).  The origin and development of factor analysis.  Applied Statistics, 2, 107-117.

2A - Costello, A. B., & Osborne, J. W. (2005).  Best practices in exploratory factor analysis: Four recommendations for getting the most from your analysis.  Practical Assessment, Research, and Evaluation, 10. Available online: http://pareonline.net/getvn.asp?v=10&n=7

3A - Russell, D. W. (2002). In search of underlying dimensions: The use (and abuse) of factor analysis in Personality and Social Psychology Bulletin. Personality and Social Psychology Bulletin, 28, 1629-1646.

4A - Fabrigar, L. R., Wegener, D. T., MacCallum, R. C., & Strahan, E. J. (1999).  Evaluating the use of exploratory factor analysis in psychological research.  Psychological Methods, 4, 272-299.

Week 2 Readings:

-- Introduction (Cont.)

Chapter 2, 3 - Gorsuch

click on link for PDF - Marelich, W.D., & Clark, T. (2004).  HIV testing and false disclosures in heterosexual college students.  Journal of American College Health, 53, 109-115.

5a) Floyd, F. J., & Widaman, K. F. (1995).  Factor analysis in the development and refinement of clinical assessment instruments.  Psychological Assessment, 7, 286-299.

6a) Gorsuch, R. L. (1997).  Exploratory factor analysis: Its role in item analysis.  Journal of Personality Assessment, 68, 532-560.

7a) Reis, S. P., Waller, N. G., & Comrey, A. L. (2000).  Factor analysis and scale revision. Psychological Assessment, 12, 287-297.

8a) Thompson, B., & Daniel, L.G. (1996).  Factor analytic evidence for the construct validity of scores: A historical overview and some guidelines.  Educational and Psychological Measurement, 56, 197-208.

Week 3 Readings:

-- Assumptions and Data/Sample Size Issues

Gorsuch Chapters 4,5,6

9b) Tabachnick, B. G., & Fidell, L. S. (2001).  Using multivariate statistics (4th ed., pp. 588-590).  Boston: Allyn and Bacon. 

10b) MacCallum, R. C., & Widaman, K. F. (1999).  Sample size in factor analysis.  Psychological Methods, 4, 84-99.

11b) Atkinson, L. (1988).  The measurement-statistics controversy: Factor analysis and subinterval data.  Bulletin of the Psychonomic Society, 26, 361-364.

Week 4 Readings:

-- On factor Solutions and Rotation Fit

Gorsuch Chapters 8,9,10

12b) Cliff, N. (1988).  The eigenvalues-greater-than-one rule and the reliability of components.  Psychological Bulletin, 103, 276-279.

Week 5 Readings:

-- On Parallel Analysis, etc.

13b) Horn, J.L. (1965).  A rationale and test for the number of factors in factor analysis.  Psychometrica, 30, 179-185.

14b) Lautenschlager, G.L. (1989).  A comparison of alternatives to conducting Monte Carlo analyses for determining parallel analysis criteria.  Multivariate Behavioral Research, 24, 365-395.

15b) O’Connor, B.P. (2000).  SPSS and SAS programs for determining the number of components using parallel analysis and Velicer’s MAP test.  Behavior Research Methods, Instruments, and Computers, 32, 396-402.

Week 6 Readings:

--- PCA issue with highly correlated items

16b) Ramsey, F.L. (1986).  A fable of PCA.  The American Statistician, 40, 323-324. 

---- Introduction to SEM and CFA

17c) Lei, P., & Wu, Q. (2007). Introduction to structural equation modeling: Issues and practical considerations. Educational Measurement, Issues and Practice, 26, 33-43.

Byrne -- Part 1, Part 2 (Application 1 and 2)

Week 7 Readings:

---- On fit and reporting of SEM and CFA

18c) Marsh, H. W., & Balla, J. (1994). Goodness of fit in confirmatory factor analysis: The effects of sample size and model parsimony.  Quality and Quantity, 28, 185-217.

19c) McDonald, R. P., & Ho, M. R. (2002). Principles and practice in reporting structural equation analyses.  Psychological Methods, 7, 64-82.

20c) Marsh, H. W., Hau, K., & Wen, Z. (2004). In search of golden rules: Comment on hypothesis-testing approaches to setting cutoff values for fit indexes and dangers of overgeneralizing Hu and Bentler's (1999) findings. Structural Equation Modeling, 11, 320-341.

21c) Hu, L., & Bentler, P. M. (1999).  Cutoff criteria for fit indexes in covariance structural analysis: Conventional criteria versus new alternatives. Structural Equation Modeling, 6, 1-55.

Week 8 Readings:

---CFA Continued

22d) Anderson, J.C., & Gerbing, D.W. (1988).  Structural  equation modeling in practice: A review and recommended

two-step approach.  Psycholgical Bulletin, 103, 411-423.

23d) Prooijen, J., & Kloot, W.A. (2001).  Confirmatory analysis of exploratively obtained factor structures.  Educational and Psychological Measurement, 61, 777-792.

24d) Gerbing, D.W., & Hamilton, J.F. (1996). Viability of exploratory factor analysis as a precursor to confirmatory factor analysis.  Structural Equation Modeling, 3, 62-72.

--CFA and 2nd-Order FA

25) Marelich, W.D., Lundquist, J., Painter, K., & Mechanic, M.B. (2008). Sexual deception as a social-exchange process:  Development of a behavior-based sexual deception scale.  The Journal of Sex Research, 45, 27-35.

Week 9 Readings:

--CFA and 2nd-Order FA Continued

26) Murphy, D.A., Marelich, W.D., & Hoffman, D. (2000).  Assessment of anxiety and depression in young children: Support for two separate constructs. Journal of Clinical Child Psychology, 29, 383-391.

27e) Rindskopf, D., & Rose, T. (1988).  Some theory and applications of confirmatory second-order factor analysis.  Multivariate Behavioral Research, 23, 51-67.

-Byrne -- Chapter 5

-Gorsuch -- Chapter 11

-EQS Program

Week 10 Readings:

--CFA and Multi-group Analyses

-Bryne -- Chapter 7 (all - the way we do it now)

-Gorsuch --Chapter 5 (old school approach)

28) Murphy, D. A., Rotheram-Borus, M.J., & Marelich, W.D. (2003).  Factor structure of a coping scale across two samples.  Journal of Applied Social Psychology, 33, 627-647.

29e) Werts, C. E., Rock, D. A., Linn, R. L., & Joreskog, K. G. (1976). Comparison of correlations, variances, covariances, and regression weights with or without measurement error. Psychological Bulletin, 83(6), 1007-1013. doi:10.1037/0033-2909.83.6.1007

Week 11 Readings:

-CFA and missing data, bootstrap

-Bentler (EQS program manual) -- Chapters 12-13

30) [applied example for a covariance structural model] Murphy, D.A., Marelich, W.D., & Amaro, H. (2009).  Maternal HIV/AIDS and adolescent depression: A covariance structure analysis of the ‘Parents and Adolescents Coping Together’ (PACT) model.  Vulnerable Children and Youth Studies, 4, 67-82. doi:10.1016/j.jadohealth.2011.12.025

-Factor analysis and Cluster/MDS analyses

31f) Liau, A., Tan, T., & Khoo, A. (2011). Scale measurement: Comparing factor analysis and variable clustering.  SAS Global Forum, Paper 352-2011.

32f) Tucker-Drob, E. M., & Salthouse, T. A. (2009).  Confirmatory factor analysis and multidimensional scaling for construct validation of cognitive abilities.  International Journal of Behavioral Development, 33, 277-285.

33) Gorsuch, Chapter 9 (end of chapter), Chapter 12

-Close-out of Factor Analysis, pros/cons

34) Gorsuch, Chapters 17-18



The presentations should be geared toward an audience of individuals who are part of the class.  You should include the following:

1 - overview of the technique/problem area

2 - how the technique you are using works

3 - decisions you had to make in the analyses

4 - how things could go wrong (probs with the data, caveats, etc.), maybe some diagnostics

5 - application of the technique, and interpretation

Presentations are scored on clarity, accuracy, depth/effort. These scores will be on a 1-12 scale (6 weak, 8 ok, 10 good, 12 excellent). To get beyond a '10' on these, you have to go above/beyond what is expected of your chosen technique.  Powerpoint is okay although i'm not a huge fan, and prefer handouts and an actual presentation, not just reading slide lines.  Your presentations should be 15-20 minutes long (no longer).


Paper should generally have the look/feel of one of our "thicker" assignments in terms of assessing and summarizing the assumptions and the statistical techniques you applied.  Also include all output (or most output), syntax, and annotate your output.

It should also have a typical APA research paper flow...Introduction, Method, Results, Discussion, References.  APA format generally should be followed, but minor 'misses' on formatting are okay. If you are using secondary data, do not plagiarize, but check the APA manual on how to appropriately summarize secondary data methods.  If you collected the data yourself, provide typical Procedures section, etc.

Make sure you cover the following:

1 - overview of the substantive issue you are exploring (i.e. - the topic area)...if you are investigating Romantic Jealousy using factor analysis, the substantive area is Romantic Jealousy, so you need to write a few pages at least on the topic including references.

2 - introduction/summary of the EFA or CFA approach you are applying to solve or evaluate the problem/issue from #1

3 - decisions you had to make in the analysis

4 - how things could go wrong (probs with the data, caveats, etc.), maybe some diagnostics

5 - assumptions

6 - application of the technique, and interpretation

7 - Discussion of the Results as they pertain to your substantive area.

In essence, you are writing a research article that is applying or investigating some substantive issue.

Q: How long should be paper be?

A: Expect at least 10-20+ written pages (excluding Tables/References/Statistical OUTPUT).  What will end up being turned in will be a packet that is inclusive of everything, including your annotated output, and syntax.  With tables, references/stat output, its possible your packet could be 40+ pages.

Q: Scoring?

A: Yes...same format as the Presentations