Using spatial, hierarchical, and econometric models in urban data-poor areas to examine food security

  • Anna Carla Lopéz-Carr San Diego State University Department of Geography, San Diego, CA. USA
  • David Lopéz-Carr University of California, Department of Economics, Santa Barbara, CA. USA
  • Laura Grant University of California, Department of Geography, Santa Barbara, CA. USA
  • John Weeks San Diego State University Department of Geography, San Diego, CA. USA

Abstract

In this paper we explore three models of food security in Accra, Ghana. We use survey data from the 2003 Women’s Health Study in Accra and satellite imagery from 2002 Quickbird satellite imagery to examine socio-economic, spatial, and environmental predictors of food insecurity (defined as poorly nourished households). The spatial model highlights areas of particular concern “hotspots” with statistically significant values. The hierarchical model separated the relative effects of household versus neighborhood level variables. The econometric model emphasized economic trends among household based on estimated values of household wealth. Together, results suggest that, while the data source is the same, outcomes differ, highlighting the caution researchers must use when determining an appropriate statistical approach. The choice of statistical model may point the researcher towards a path of ecological fallacy or delightful parsimony. Together, these three models allow us to draw a more complete picture of food security patterns in Accra, and to draw important and more comprehensive conclusions for policy recommendations.

Published
2017-09-30
How to Cite
LOPÉZ-CARR, Anna Carla et al. Using spatial, hierarchical, and econometric models in urban data-poor areas to examine food security. Plurimondi, [S.l.], n. 17, sep. 2017. ISSN 2420-921X. Available at: <http://plurimondi.poliba.it/index.php/Plurimondi/article/view/32>. Date accessed: 14 oct. 2019.