Factor extraction in exploratory factor analysis for ordinal indicators: Is principal component analysis the best option?

Researchers continue to choose PCA in scale development and adaptation studies because it is the default setting and overestimates measurement quality. When PCA is utilized in investigations, the explained variance and factor loadings can be exaggerated. PCA, in contrast to the models given in the literature, should be investigated in categorical/ordered, severely skewed data, and multidimensional structures. The purpose of this study is to compare the relative bias and percent correct estimation of PCA, PAF, and MINRES techniques with Monte Carlo simulations. In Monte Carlo simulations sample size, level of skewness, number of categories, average factor loadings, number of factors, level of inter-factor correlation and test length were manipulated. The results show that PCA overestimates most models with lower average factor loadings, but PAF and MINRES provide unbiased results even with low factor loadings. PAF and MINRES produce more accurate and impartial results, and it is projected that PCA will lead researchers to believe that the items in scale development or adaptation studies are of "high quality."