Robust Spatial Durbin Model Untuk Pemodelan Tingkat Pengangguran Terbuka di Provinsi Jawa Tengah

Abstract

Unemployment is still a very crucial problem faced by the Indonesian state. The Central Bureau of Statistics noted that the number of unemployed in Indonesia in 2019 was 4.44 percent, an increase of 2.04 percent in 2020. The purpose of this study was to find out the characteristics of the spatial pattern and modeling the open unemployment rate in Central Java Province. Removing outliers in spatial analysis can change the composition of the spatial effects on the data. One method of solving due to outliers in the spatial regression model is using spatial robust regression. Robust Spatial Durbin Model method which is one of the methods used when spatial outliers occur. The results showed that there are spatial pattern characteristics and modeling for each dependent and independent variable which are different from the independent variables which are mutually correlated. In addition, the RSDM model is a better model than the OLS and SDM models in modeling the Open Unemployment Rate in Central Java Province in 2021 because it has an R2 value of 49.85% and the smallest AIC value of 22,563.