ANALISIS PERBANDINGAN METODE FORWARD DAN BACKWARD DALAM PEMODELAN REGRESI LINEAR BERGANDA

Abstract

The issue of health insurance costs has become a major concern in the healthcare system in the USA. Determining the accurate health insurance cost is crucial for individuals and families who rely on health insurance for financing their healthcare. This research aims to compare the most effective methods for determining health insurance costs using variable selection methods in multiple linear regression models. The variable selection methods used are forward selection and backward elimination. Based on the application in the regression model, the forward selection method yielded dan RMSE values of 79.68% and 2024.295, respectively. The backward elimination method produced dan RMSE values of 96.77% and 807.175, respectively. The most effective variable selection method for determining health insurance costs in this case is backward elimination.