PERBANDINGAN METODE ORDINARY LEAST SQUARE (OLS) DAN REGRESI ROBUST PADA FAKTOR YANG MEMPENGARUHI ANGKA HARAPAN HIDUP DI PROVINSI JAWA TENGAH

Abstract

This study aims to determine the factors that affect life expectancy in Central Java Province. The analytical method used is OLS (Ordinary Least Square) which is a regression method that minimizes the number of quadratic errors and robust regression method is a regression method used when the distribution of the error is not normal or the existence of the influence of the model. In this study, it was found that robust method is better than OLS method. In this study researchers used secondary data obtained from the Central Bureau of Statistics of Central Java Province in 2014. In this study diporelah results that the two methods are normally distributed. In the OLS and robust methods, significant variables are GRDP, PHBS and Health Services while the insignificant variables in the OLS and robust methods are School Enrollment Rates. However, from both methods the best model is robus method with r square value of 0.4414
Keywords: Education, Health Services, PHBS, PDRB, life expectancy, OLS, Robust method