Application of the MAP Method Using jamovi: An Implementation and Empirical Analysis

This study introduces the development and validation of Velicer’s Minimum Average Partial (MAP) test within the seolmatrix module of the jamovi statistical software, addressing a methodological gap in the accessibility of advanced factor retention techniques. Determining the optimal number of factors or components to retain in exploratory factor analysis (EFA) and principal component analysis (PCA) remains one of the most fundamental challenges in multivariate statistics. Conventional approaches—such as the Kaiser criterion (eigenvalues > 1) and the scree plot—have been criticized for their susceptibility to overestimation and the subjective interpretation of dimensionality. The implemented seolmatrix module (Version 4.0.6) extends the jamovi environment by supporting multiple correlation types (Pearson, Kendall, Spearman, Gamma, and Polychoric), providing both numerical and graphical outputs, and enabling comparative analyses with other factor retention criteria, including the Empirical Kaiser Criterion and the HULL method. Empirical validation using the Big Five Inventory personality dataset demonstrated that the MAP test accurately identified the theoretical five-factor structure, whereas the Kaiser criterion overestimated six factors. Furthermore, the convergence of the MAP test results with those from parallel analysis and the Empirical Kaiser Criterion provided strong statistical support for the theoretical five-factor model. The successful implementation of the MAP test within an open-source, user-friendly platform exemplifies how advanced statistical methodologies can be democratized without compromising analytical rigor or interpretive precision, thereby contributing to the enhancement of methodological sophistication and reproducibility in social and behavioral sciences.