ABSTRACT
Factor analysis belongs to a family of methods which involve what are called latent variables. Often, particularly in social science research, we cannot directly measure the variables of major interest. Examples of such concepts are intelligence, political attitude (left-wing, moderate, or right-wing), and socioeconomic status. Although we use these concepts in social science discourse as if they were just like any other variable, they differ from other variables in that they cannot be observed — which is why they are called latent. In some cases, a concept may be represented by a single latent variable, but often they are multidimensional in nature and so involve more than one latent variable. Suppose that there are q latent variables, denoted by f1, f2, . . . , fq. These latent variables are commonly called factors which is why we denote them by f . Latent variable methods, of which factor analysis is the oldest and most widely used, form the subject of this and the next three chapters.
