Mixed Geographically and Temporally Weighted Autoregressive to Modeling the Levels of Poverty Population in Java in 2012-2018

Abstract

Geographically and temporally weighted regression (GTWR) is a method applied when there is spatial and temporal diversity in the observation. In the GTWR model not all variables were local or insignificant (global in nature) so the GTWR model was developed into Mixed Geographically and Temporally Weighted Regression (MGTWR). The GTWR model can also add an autoregressive component of response variable, the resulting model is known as a geographically and temporally weighted autoregressive model (GTWAR). This study develops the MGTWR model and the GTWAR model which produces a Geographically and Temporally Weighted Autoregressive model (MGTWAR) which is used to model data on the percentage of poor people in regency/municipality on Java Island in 2012-2018. The results showed that MGTWAR produced Akaike Information Criterion (AIC) smaller than GTWR, and the coefficient of determination (R2) is higher than GTWR.