Comparison of Geographically Weighted Regression Analysis and Global Regression on Modeling the Unemployment Rate in West Java
- 10.2991/aer.k.201221.078How to use a DOI?
- Unemployment Rate, Geographically Weighted Regression, West Java
This study aims to identify the factors Unemployment Rate (UR) in West Java and develop the appropriate model. This study applied the location (spatial) element using Geographically Weighted Regression (GWR). The GWR model was compared with the global regression. The data used in this study are secondary data on 2017 UR for 27 cities/ regencies in West Java. The dependent variable (Y) is the Unemployment Rate (UR), the independent variables include Population Density Level (PDL), Gross Regional Domestic Product(GRDP), Regional Minimum Wage (RMW), Level of Active Labor Participation Rate (ALPR), and Human Development Index (HDI). The results show that the GWR model provides a coefficient of determination (R2) more significant than the global regression model. The Akaike Information Criteria (AIC) value of the GWR model is smaller than the global regression model, meaning that the local regression model of error value is smaller than the global regression model. In other words, the local regression model is better than the global regression model. The factor affecting UR globally is RMW. There are 27 different combinations of local regression models according to the number of cities/regencies in West Java.
- © 2020, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Euis Sartika AU - Anny Suryani PY - 2020 DA - 2020/12/22 TI - Comparison of Geographically Weighted Regression Analysis and Global Regression on Modeling the Unemployment Rate in West Java BT - Proceedings of the International Seminar of Science and Applied Technology (ISSAT 2020) PB - Atlantis Press SP - 472 EP - 478 SN - 2352-5401 UR - https://doi.org/10.2991/aer.k.201221.078 DO - 10.2991/aer.k.201221.078 ID - Sartika2020 ER -