Application of the Geographically Weighted Regression Method to the Human Development Index and Visualization on the Tableau Dashboard

Abstract

Spatial data is information that contains the location or geographic information of a region on a map of objects on Earth. One of the methods in spatial analysis is Geographically Weighted Regression (GWR). GWR is the development of the Ordinary Least Square (OLS) theory into a weighted regression model that takes into account spatial effects, resulting in a parameter estimator that can only be used to predict each point or location where the data is observed and concluded. The application of the GWR method is expected to produce an accurate Human Development Index (HDI) model. This study applies the GWR method to the Human Development Index in each Regency or city in Central Java in 2021. With a global GWR determination coefficient value of 0.8577, it means that 85.77% of population density, percentage of the poor population, gross regional domestic product at constant prices, and adjusted school enrollment rates have a global influence on HDI. From the GWR model obtained, it is known that the value of the HDI variable will decrease if the value of the PPM variable increases by one unit in each Regency or city. The value of the IPM variable will increase if the value of the PDRB, KP, and APS variables increases by one unit in each Regency or city. Therefore,
Regency or city governments in Central Java Province are expected to be able to overcome the problem of poverty and reduce the percentage of poor people so that there is an increase in the HDI.