I am modeling Exploratory Factor Analysis in R, Python, Mplus, and SPSS with maximum likelihood method and Varimax orthogonal rotation. However, each software gives different measures of fit and I am not sure which of the following measures of fit confirms the validity of Factor analysis:
Following are two previous studies which mention the first two measures in their EFA model whereas in other studies some or combination of all six is mentioned:
Börjesson M, Hamilton CJ, Näsman P, Papaix C (2015) Factors driving public support for road congestion reduction policies: Congestion charging, free public transport and more roads in Stockholm, Helsinki, and Lyon. Transp Res Part A Policy Pract 78:452–462. https://doi.org/https://doi.org/10.1016/j.tra.2015.06.008
Li L, Bai Y, Song Z, et al (2018) Public transportation competitiveness analysis based on current passenger loyalty. Transp Res Part A Policy Pract 113:213–226. https://doi.org/https://doi.org/10.1016/j.tra.2018.04.016
Please assist me with this problem.
Since this has an SPSS tag on it, I'll reply with regard to what SPSS offers for exploratory factor analysis in the FACTOR procedure. As others have mentioned, the Bartlett sphericity test and the KMO statistic are basically sanity checks on whether you have something in common as the basis for a common factor analysis. The other measures are for goodness of fit of the data to the model. The only one of these available in FACTOR is a chi-square test for maximum likelihood and generalized least squares estimation. This basically gives you information on whether the data are a poor fit for the model (with a small p value) and more factors are required to improve the fit.