Investigation of affective traits affecting mathematics achievement by SEM and MARS methods

The purpose of the study is to analyze affective traits that affect mathematics achievement through Structural Equation Modeling (SEM) as a traditional regression model and Multivariate Adaptive Regression Splines (MARS), one data mining methods. Modeling, regression-based methods, quite popular for social sciences due various advantages it offers; however, requires very intensive assumptions. MARS method, on other hand, multivariate adaptive nonparametric statistical method used classification modeling. does not need any assumptions such normality, linearity, homogeneity. It allows variables do provide linearity be included in analysis. present examines whether possible use which more flexible compared SEM, taking both methods into account. Regarding this goal, SEM was created with program R using variable picked from TIMMS 2019 data. Then, SPM (Salford Predictive Modeler) program. results showed at certain points gave similar compatible literature.