The Examination of Model Fit Indexes with Different Estimation Methods under Different Sample Sizes in Confirmatory Factor Analysis

In adjustment studies of scales and in terms of cross validity at scale development, confirmatory factor analysis is conducted. Confirmatory factor analysis, multivariate statistics, is estimated via various parameter estimation methods and utilizes several fit indexes for evaluating the model fit. In this study, model fit indexes utilized in confirmatory factor analysis are examined with different parameter estimation methods under different sample sizes. For the purpose of this study, answers of 60, 100, 250, 500 and 1000 students who attended PISA 2012 program were pulled from the answers to two dimensional “thoughts on the importance of mathematics” dimension. Estimations were based on methods of maximum likelihood (ML), unweighted least squares (ULS) and generalized least squares (GLS). As a result of the study, it was found that model fit indexes were affected by the conditions, however some fit indexes were affected less than others and vice versa. In order to analyze these, some suggestions were made.