ABSTRACT
Multivariate analysis procedures have been developed to help researchers manage large databases. This chapter examines the techniques to analyze the data sets in are Principal Component Analysis (PCA), Standard Factor Analysis (SFA), and cluster analysis. Factor analysis serves many different purposes, the most important of which are reducing the number of variables and hypothesis testing. Factor analysis requires the researcher to subjectively interpret each factor based on the variables that load on the factor, which some believe to be one of the greatest advantages of factor analysis. PCA is similar to SFA in concept and application; it is one of seven different ways that IBM SPSS provides for extracting the factors that underlie a set of measurements. Cluster analysis results in a reduction in the amount of data with which the researcher must work, but it involves more subjective decision making than factor analysis. However, cluster analysis remains a popular tool for grouping people into similar categories.
