PEMODELAN SEEMINGLY UNRELATED REGRESSION PADA INDEKS PEMBANGUNAN GENDER DI PROVINSI SUMATERA UTARA TAHUN 2020

Abstract

The population in North Sumatra Province consists of 14.8 million people with a sex ratio of 95.60%. The disparity between women and men in North Sumatra Province is still quite high in the health, education and employment sectors. This study aims to determine the Seemingly Unrelated Regression model on the gender development index in North Sumatra Province and determine the factors that influence it. The Seemingly Unrelated Regression model is a system of equations consisting of several equations that are interconnected with each other because the errors between the different equations are correlated. Ordinary Least Square estimation can be used to estimate the parameters of each equation but the weakness of Ordinary Least Square can eliminate information about the possibility of a relationship between equations. Seemingly Unrelated Regression modeling is carried out using robust S estimation because the data used contains outliers. Based on the results of the analysis that have a significant effect on the gender development index in the male population are the sex ratio, life expectancy, and the type of education completed at the high school level, while for the female population it is the type of education completed by the senior high school level.