Geographically Weighted Panel Regression (GWPR) and Geographically and Temporally Weighted Regression (GTWR) Methods in the Influence of Factors Affecting the Minimum Wage of Each Province in Indonesia

Authors

  • Apriani Monica Renta Department of Mathematics, University of Lampung, Bandar Lampung, Lampung, Indonesia
  • Herawati Netti Department of Mathematics, University of Lampung, Bandar Lampung, Lampung, Indonesia
  • Sutrisno Agus Department of Mathematics, University of Lampung, Bandar Lampung, Lampung, Indonesia
  • Widiarti Department of Mathematics, University of Lampung, Bandar Lampung, Lampung, Indonesia

DOI:

https://doi.org/10.31305/rrijm.2024.v09.n07.015

Keywords:

GWPR, GWR, GTWR, CV, Kernel Weights

Abstract

The study compares the Geographically Weighted Panel Regression (GWPR) method and the Geographically Temporal Weighted Regression (GTWR) method using a spatial and temporal approach in the data. Both of these methods are developments by one of the Geographically Weighted Regression (GWR) methods. GWPR, which is a combination of the GWR model with panel data regression to analyze spatial variations between regions on the influence of the provincial minimum wage determination factor in Indonesia. Meanwhile, GTWR is used to analyze the presence of non-stationarity in its data if there is spatial and temporal simultaneously. In this study, both methods, namely GWPR and GTWR, will show variations in the influence of variables in each location by showing their local parameters with kernel weighting. In selecting the optimum bandwidth of the kernel weight function using cross validation (CV) with the minimum value to be used. After that, when measuring the best model of the two methods, which is GWPR and GTWR, it will be shown by the largest R2 value, RMSE and, AIC with the smallest value. From the results of the study between GWPR and GTWR, namely the GTWR method has an R2 value (93.73%) and the GWPR method has an R2 value (67.32%). Therefore, the R2 value of the GTWR method is greater than the GWPR method. The results of the study indicate that the GTWR method is a better method in handling spatial-temporal.

References

Fotheringham, A.S. Brundson, C. & Charlton, M. Geographically Weighted Regression: Analysis of Spatially Varying Relationship. England: John Wiley and Sons Ltd. 2002.

Gatrell, A. C., & Bailey, T. C. Interactive Spatial Data Analysis in Medical Geography. In Soc. Sci. Med1996; 42(6): 843-855.

Haining, R. P. Spatial Data Analysis: Theory and Practice. England: Cambridge University Press. 2003.

Huang, B., Wu, B., & Barry, M. Geographically and temporally weighted regression for modeling spatio-temporal variation in house prices. International Journal of Geographical Information Science2010; 24(3), 383–401.

Li, C., & Managi, S. Estimating monthly global ground-level NO2 concentrations using geographically weighted panel regression. Remote Sensing of Environment2022; 280.

Liu, J., Yang, Y., Xu, S., Zhao, Y., Wang, Y., & Zhang, F. A geographically temporal weighted regression approach with travel distance for house price estimation. Entropy2016; 18(8): 1-13.

Ma, X., Zhang, J., Ding, C., & Wang, Y. A geographically and temporally weighted regression model to explore the spatiotemporal influence of built environment on transit ridership. Computers, Environment and Urban Systems2018; 70: 113–124.

Que, X., Ma, C., Ma, X., & Chen, Q.Parallel computing for Fast Spatiotemporal Weighted Regression. Computers and Geosciences2021;150: 4-13

Ratnasari, V., Audha, S. H., & Dani, A. T. R. Statistical modeling to analyze factors affecting the middle-income trap in Indonesia using panel data regression. In MethodsX2023; 11: 1-9.

Shen, Y., de Hoogh, K., Schmitz, O., Clinton, N., Tuxen-Bettman, K., Brandt, J., et al. Europe-wide air pollution modeling from 2000 to 2019 using geographically weighted regression. Environment International2022; 168: 107485

Uyanık, G. K., & Güler, N. A Study on Multiple Linear Regression Analysis. Procedia - Social and Behavioral Sciences2013; 106: 234–240.

Wrenn, D. H., & Sam, A. G. Geographically and temporally weighted likelihood regression: Exploring the spatiotemporal determinants of land use change. Regional Science and Urban Economics2014; 44(1): 60–74.

Xu, X., Luo, X., Ma, C., & Xiao, D. Spatial-temporal analysis of pedestrian injury severity with geographically and temporally weighted regression model in Hong Kong. Transportation Research Part F: Traffic Psychology and Behaviour2020; 69: 286–300.

Yu, D., Zhang, Y., Wu, X., Li, D., & Li, G. The varying effects of accessing high- speed rail system on China’s county development: A geographically weighted panel regression analysis. Land Use Policy2021;100: 104935.

Zhao, C., Tang, J., Zeng, Y., Li, Z., & Gao, F. (2023). Understanding the spatio-temporally heterogeneous effects of built environment on urban travel emissions. Journal of Transport Geography2023; 112: 103689

Downloads

Published

15-07-2024

How to Cite

Renta, A. M., Netti, H., Agus, S., & Widiarti. (2024). Geographically Weighted Panel Regression (GWPR) and Geographically and Temporally Weighted Regression (GTWR) Methods in the Influence of Factors Affecting the Minimum Wage of Each Province in Indonesia. RESEARCH REVIEW International Journal of Multidisciplinary, 9(7), 106–115. https://doi.org/10.31305/rrijm.2024.v09.n07.015