Open AccessSpatial Modeling for Poverty: The Comparison of Spatial Error Model and Geographic Weighted Regression
Author(s) -
Achi Rinaldi,
Yuni Susianto,
Budi Santoso,
Wahyu Kusumaningtyas
Publication year - 2021
Publication title -
al-jabar
Language(s) - English
Resource type - Journals
eISSN - 2540-7562
pISSN - 2086-5872
DOI - 10.24042/ajpm.v12i1.8671
Subject(s) - geographically weighted regression , variance (accounting) , spatial analysis , statistics , regression analysis , regression , econometrics , spatial ecology , poverty , spatial variability , spatial heterogeneity , linear regression , spatial dependence , geography , mathematics , ecology , accounting , economics , business , biology , economic growth
This study aims to analyze poverty using spatial models. The researchers also compared the Spatial Error Model (SEM) and Geographically Weighted Regression (GWR). The comparison of the two models was based on the estimation evaluation criteria and the constructed spatial associations. Spatial regression is considered very appropriate to be used to model the relationship pattern between poverty and explanatory variables when the observed data has a spatial effect caused by the proximity between the observation areas. The spatial dependence of errors on observational data can be overcome using SEM, while the effect of heterogeneity of spatial variance can overcome using GWR.