This chapter presented extensive examples of principal components analysis and factor analysis. The PCA analysis began with a flat file of individual observations and produced a two-component solution for aggregate state-level (plus DC) crime rates for seven violent crimes. This analysis led to insights into both the variables and the observations in the analysis. The FA analysis began with a correlation matrix, of various ability tests, on 112 individuals, and produced a two-factor solution that showed evidence of two subsets of tests, along with a general item that loaded on both factors.
In the next chapter, we will look at cluster analysis, which is a technique for grouping observations into clusters that are hopefully homogeneous and well separated.
