Assessing Construct Validity: The Utility of Factor Analysis

Abstract

According to validity standards of American Psychological Association in 1954, four types of validity were identified for accomplishing different aims of research, namely content validity, predictive validity, concurrent validity, and construct validity. For the justification of the construct validity, this study utilizes exploratory factor analysis and confirmatory factor analysis to examine factors of the empirical data. Through the operation of the empirical data analysis, important results are accordingly illustrated by the exploratory factor analysis such as factor loading, the rotated simple structure, the plot of scree test; also by the confirmatory factor analysis such as specifying a priori factor pattern, and indices for goodness of model fit. Consequently, the obtained solutions from the factor analysis procedures provide reasonable justification to construct validity of the researched.