Comparison of Generalized Additive Models and Multivariate Adaptive Regression Splines (Case Study: Modeling of Grade Point Average of IPB and STAIN Purwokerto Students)
Abstract
Regression analysis is used to capture influences of independent variables to dependent ones. It can be done in two ways, parametric and nonparametric approach. The parametric approach needs assumptions, while nonparametric approach is more flexible than the parametric one. The nonparametric approach used in this research is Generalized Additive Models (GAM) and Multivariate Adaptive Regression Splines (MARS). Essentially, GAM and MARS can accommodate nonlinearity data.