Application of Spatial Regression Models to Income Poverty Ratios in Middle Delta Contiguous Counties in Egypt

Sohair F Higazi, Dina H. Abdel-Hady, Samir Ahmed Al-Oulfi

Abstract


Regression analysis depends on several assumptions that have to be satisfied. A major assumption that is never satisfied when variables are from contiguous observations is the independence of error terms. Spatial analysis treated the violation of that assumption by two derived models that put contiguity of observations into consideration. Data used are from Egypt's 2006 latest census, for 93 counties in middle delta seven adjacent Governorates. The dependent variable used is the percent of individuals classified as poor (those who make less than 1$ daily). Predictors are some demographic indicators. Explanatory Spatial Data Analysis (ESDA) is performed to examine the existence of spatial clustering and spatial autocorrelation between neighboring counties. The ESDA revealed spatial clusters and spatial correlation between locations. Three statistical models are applied to the data, the Ordinary Least Square regression model (OLS), the Spatial Error Model (SEM) and the Spatial Lag Model (SLM).The Likelihood Ratio test and some information criterions are used to compare SLM and SEM to OLS. The SEM model proved to be better than the SLM model. Recommendations are drawn regarding the two spatial models used.


Keywords


Spatial Regression, Spatial Error Model, Special Lag Model, GeoDa, ESDA, LISA Maps.

Full Text:

PDF


DOI: http://dx.doi.org/10.18187/pjsor.v9i1.272

Refbacks

  • There are currently no refbacks.




Copyright (c)

Title

Application of Spatial Regression Models to Income Poverty Ratios in Middle Delta Contiguous Counties in Egypt

Keywords

Spatial Regression, Spatial Error Model, Special Lag Model, GeoDa, ESDA, LISA Maps.

Description

Regression analysis depends on several assumptions that have to be satisfied. A major assumption that is never satisfied when variables are from contiguous observations is the independence of error terms. Spatial analysis treated the violation of that assumption by two derived models that put contiguity of observations into consideration. Data used are from Egypt's 2006 latest census, for 93 counties in middle delta seven adjacent Governorates. The dependent variable used is the percent of individuals classified as poor (those who make less than 1$ daily). Predictors are some demographic indicators. Explanatory Spatial Data Analysis (ESDA) is performed to examine the existence of spatial clustering and spatial autocorrelation between neighboring counties. The ESDA revealed spatial clusters and spatial correlation between locations. Three statistical models are applied to the data, the Ordinary Least Square regression model (OLS), the Spatial Error Model (SEM) and the Spatial Lag Model (SLM).The Likelihood Ratio test and some information criterions are used to compare SLM and SEM to OLS. The SEM model proved to be better than the SLM model. Recommendations are drawn regarding the two spatial models used.


Date

2013-02-25

Identifier


Source

Pakistan Journal of Statistics and Operation Research; Vol. 9 No. 1. 2013



Print ISSN: 1816-2711 | Electronic ISSN: 2220-5810