Pemodelan Indeks Pembangunan Manusia Di Jawa Timur Dengan Metode Geographically Weighted Lasso (GWL)

Abstract

The human development index is the achievement of development results in a region or region to assess the high or low quality of life. Human development index data in East Java has spatial relationships of variable values or locations which are thought to have an impact on spatial dependence so that the Geographically Weighted Regression (GWR) method can be used. The aim of this research is to find out what factors influence the Geographically Weighted Lasso (GWL) and to carry out the best modeling of the GWR and GWL methods. GWL is a technique using the lasso approach in the GWR model to overcome multicollinearity. Comparison between GWR and GWL uses RMSE and R-Square (R2) values. The RMSE value of the GWR model < GWL (0.912865 < 0.9738519). The R2 value of the GWR model is 0.966797, while the GWL is 0.962212. Based on these values, it is concluded that the GWR model has better accuracy in explaining the human development index in East Java Province.