How to judge factor analysis—not just run it.
This concise guide explains why reliability and usefulness matter when interpreting factor results, and what readers should look for to avoid misreading random data as meaningful findings.
The content frames the scope of factor analysis, outlines practical methods for testing reliability, and discusses how to compare real data with simulated results. It also offers a clear look at how researchers can improve reporting and interpretation in their studies.
- Practical methods for checking reliability, including split samples, a priori modeling, and Monte Carlo simulation
- How to assess the usefulness of a factor analysis beyond face validity
- Common decisions that shape results, such as variable choice, sample size, and extraction methods
- Guidance on interpreting factor loadings, variance explained, and model assumptions
Ideal for readers of research methods and applied psychology who want to understand how factor analyses should be evaluated and reported.
Professor Armstrong is the author of Long-Range Forecasting and he is a founder of the Journal of Forecasting, the International Journal of Forecasting, the International Institute of Forecasting and the International Symposium on Forecasting. For additional information on the book and on the Forecasting Principles Project, see http: //hops.wharton.upenn.edu/forecast