Bootstrap Simulation Procedure Applied to the Selection of the Multiple Linear Regressions

This article considers the analysis of multiple linearregressions (MLR) that is used frequently in practice. We proposenew approach could be used to guide the selection of the “true”regression model for different sample size in both cases of existingand not existing of multicollinearity, first-order autocorrelation, andheteroscedasticity. We used simulation study to compare eight modelselection criteria in terms of their ability to identify the “true” modelwith the help of the new approach. The comparison of the eight modelselection criteria was in terms of their percentage of number of timesthat they identify the “true” model with the help of the new approach.The simulation results indicate that overall, the new proposedapproach showed very good performance with all the eight modelselection criteria where the GMSEP, JP, and SP criteria provided thebest performance for all the cases. The main result of our article is thatwe recommend using the new proposed approach with GMSEP, or JP,or SP criteria as a standard procedure to identify the “true” model.