ABSTRACT
Exploratory factor analysis (EFA) is a data reduction technique similar to principal component analysis (PCA) with subtle differences in conceptualization, estimation to model adequacy testing including the purpose of the modeling. The development of factor analysis dates back to the classical works of Charles Spearman on association of two things (1904a) and general theory of intelligence (1904b). Although primarily developed in the domain of psychology, its applications spread across almost all disciplines where the issues involve the measurement of hidden things. The major purpose is to find out how many latent dimensions (or common factors) are involved in a group of measurements and what these dimensions are (Vincent, 1953). It exploits the covariance relationships of many observed variables ( X ) in search of the factors (F) and falls under covariance structure analysis. In this chapter, we discuss on the conceptual factor model with assumptions and certain useful results followed by three extraction methods. Then we discuss the model adequacy tests and different criteria to select the number of factors to be retained. Subsequently, factor rotation is described followed by the estimation of factor scores. Finally, a case study is presented which demonstrates the usefulness of EFA in solving real-world problems.
