Algorithms Error in The VisualGSCA Program

Abstract

The VisualGSCA program uses an incorrect algorithm, which results in scale inconsistencies between observed and latent variables. The observed variable is standardized, while the latent variable is normalized. This affects the calculation of the wrong estimate parameter value and the goodness-fit value of FIT and AFIT becomes inaccurate. This error occurs because the algorithm used is not a pure GSCA algorithm but a reduced GSCA algorithm that ignores the structural model, resulting in an incorrect FIT value. This study aims to prove that the old version of the GSCA program has problems using its algorithm so that it can affect the results of its statistical calculations. The data used in this study are data from previous studies that have been processed with the old version of the GSCA program, so that the results can be compared with the latest version of the GSCA program. The results obtained prove that there are indeed differences in the value of the Loading Factor and FIT, so that research that has been done previously needs to be reanalyzed using the latest program.