International Journal of Advanced Research and Publications (2456-9992)

Poverty Data Analysis In Riau Province Using Geographically Weighted Regression Model With Exponential And Tricube Adaptive Kernels

Volume 4 - Issue 1, January 2020 Edition
[Download Full Paper]

Author(s)
Mia Amiati, Arisman Adnan, Rado Yendra
Keywords
Adaptive, Eksponential, Geographically Weighted Regression, Riau Poverty, Tricube.
Abstract
one of the serious problems in Riau Province is the poverty rate. To overcome the problem the government has made various efforts, in the hope that poverty alleviation will become more directed, but these efforts have do not get effective results so a new aproach is needed to look specifically at poverty cases in each location. The regression analysis approach has often been used in predicting poverty rates, but still global and enforced at all observed locations without involving geographical location based on earth's longitude and latitude. One model could accommodate geographical effects on data is the Geographically Weighted Regression (GWR) model. The data used in this study is the poverty in Riau Province (y) and three independent factors (x) which will be modeled using the GWR model. The parameters of the model are calculated at each location, so it observation location has a local regression parameter value. The method for estimating the parameters of the GWR model is the Weighted Least Square (WLS) method. The weighti functions used are exponential and tricube adaptive kernels. The selection of optimum bandwidth use the Cross Validation (CV) method. The best selection criteria used are R^2, AIC and RMSE. The study show the GWR model with tricube adaptive kernel weighting function is better than the GWR model with an exponential adaptive kernel.
References
[1] L. Anselin, “Lagrange Multiplier Test for Spatial Dependence and Spatial Heterogeneity”, Journal of Geographically Analysis, 20 (1) , pp. 1–17, 1988.
[2] Central Statistics Agency, Riau in Figures 2018, CSA of Riau Province, 2017.
[3] C. Brundson, A. S. Fotheringham and M. E. Charlton, Geographically Weighted Regression: a Method Exploring Spatial Nonstationarity, Geographically Analysis, 28 (4) (1996), 281–298.
[4] W. S. Cleveland, “Robust Locally Weighted Regression and Smoothing Scatterplots”, Journal of the American Statistical Association, 74 (368), pp. 829–836, 1979.
[5] S. Deller, “Rural Poverty, Tourism and Spatial heterogeneity”, Annals of Tourism Research, 37 (1), pp. 180–205, 2010.
[6] M. F. Dziauddin and Z. Idris, “Use of Geographically Weighted Regression (GWR) Method to Estimate the a Effect of Location Attributes on the Resindential Property Values”, Indonesian Journal of Geography, 49 (1), pp. 97-110, 2017.
[7] N. Edayu and Syerrina, “A Statistical Analysis for Geographical Weighted Regression”, IOP Conference Series: Earth and Environmental Science, pp. 1–9. 2018.

[8] J. Foster, J. Greer and E. Thorbecke, “A Class Decomposable Poverty Measures”, The Econometric Society, 52 (3), pp. 761–766, 1984.
[9] S. Fotheringham, C. Brundson, and M. E. Charlton “Geographically Weighted Regression”, American Journal of Agricultural Economics, 28 (4), pp. 281–297, 2002.
[10] Graif and R. J. Sampson, “Spatial Heterogeneity in Effects of Immigration and Diversity on Neighborhood Homicide rates”,Homicide Stud, 13, pp. 242-260, 2009.
[11] R. Haining, Spatial Data Analysis: Theory and Practice, Cambridge, 2003.
[12] M. Helbich, W. Brunauer, E. Vaz and P. Nijkamp, “Spatial Heterogeneity in Hedonic House Price Model: the Case of Austria”, Tinbergen Institute Discussion Paper, 51, pp. 390–411, 2014.
[13] M.L. Jhingan, The Economics of Development and Planning, VrindaPublications (P) Ltd, Delhi, 2010.
[14] J. P. Lesage, “A family of Geographically Weighted Regression”, Department of Economics University of Toledo, pp. 1–36, 2001.
[15] Levitan, Program in Aid of the Poor for the 1980’s, Policy Studies In Employment And Welfare, The Johns Hopkins University Press, 1980.
[16] P. A. Samuelson and W. Nordhaus, Economics, Fourteen Edition, 1993.
[17] K. P. Sinaga, “Poverty Data Modeling in North Sumatera Province Using Geographically Weighted Regression (GWR) Method”, International Journal of Science and Research (IJSR), 4 (2), pp. 1738–1742, 2005.
[18] M.P.Todaro and S.C. Smith, Economic Development, Twelfth Edition, Pearson plc, London, 2015.