Geographically Weighted Regression with The Best Kernel Function on Open Unemployment Rate Data in East Java Province

Abstract

Unemployment is one of the problems that hinders employment development programs. Based on East Java BPS data, the Open Unemployment Rate in East Java in 2019 is about 3.92 percent. In 2020, unemployment increased by 466.02 thousand people and OUR increased by 2.02 percent to 5.84 percent in August 2020. In addition to the indicators that affect OUR, each observation location has different characteristics, so multiple linear regression modeling is not appropriate. Geographically Weighted Regression is one of the spatial analysis developed from multiple linear regression for data containing spatial heterogeneity effects. The weighting functions used for this GWR model are Kernel Fixed and Adaptive functions (Gaussian, Bi-Square, Tricube, and Exponential). The analytical step carried out in estimating the parameters is to use WLS. In the test, the best weighting was obtained, namely the Adaptive Tricube. Based on the results of the study, the GWR model with Adaptive Tricube weighted resulted in the value of R-Squared = 84.88%. However, the best model is obtained from the GWR model with exponential weighting with the smallest Akaike Information Criterion (AIC) value compared to the others, namely AIC = 86.01264 with R-Squared = 91.67.