Implementation of confirmatory factor analysis: a measuring model of reading academic achievement

Abstract

Using an empirical example, I show the differences between the statistical techniques of exploratory and confirmatory factor analysis. In social science research in our country, it is very common to use observable variables to analyze the direct relationship between these variables and the response variable. Moreover, exploratory factor analysis is too frequently used due to a lack of knowledge about the correct application of confirmatory factor analysis, since the latter requires the formulation of a hypothesis to be tested, whereas in exploratory factor analysis it is not necessary to have a clear idea of the hypothesis to be evaluated, as the researcher expects the data themselves to reveal the relationships with the response variable. Using an empirical example based on data from the 2009 PISA international assessment, I show the differences between the two approaches and the benefits of using confirmatory factor analysis to evaluate research hypotheses.