PEMODELAN REGRESI SPLINE PADA FAKTOR YANG MEMPENGARUHI TINGKAT KEMISKINAN DI INDONESIA

Abstract

Indonesia is one of the countries that is still struggling to overcome problems related to poverty. Based on official statistical news, in March 2020 the percentage of the poor population was recorded at 9.78%, which has increased periodically until September 2020 at 10.19% and in March 2021 at 10.14%, which is around 27.54 million. Although at the end of March 2022 the percentage of poor people in Indonesia decreased by 0.17% against September 2021, which is a decrease of around 0.34 million people. This study aims to model poverty in Indonesia with factors that are thought to affect it using spline nonparametric regression methods. This study obtained the best model, which is spline regression using a combination knot point (2,3,3,1,1) with a minimum GCV of 21.315. Of the five independent variables that have been tested, all variables have a significant effect on the poverty rate in Indonesia in 2021, namely the IPM, PDRB, TPT, and RLS variables.