Use of logistic regression model to identify the key determinants of poverty in kenya on the basis of DHS Data

Abstract

This study examines the determinants of poverty in Kenya. While most of the studies done on poverty determinants rely on the income, expenditure and consumption data, The data used in this study comes from the Demographic and Health Surveys,( DHS). While the DHS lack information on income or consumption expenditure, the asset index is a simpler way to circumvent the absence of the more widely used money-metric of welfare in the DHS, Sahn and Stifel(2003). The principal component analysis was used to create an asset index which gave the social economic status of each household. A Logistic regression was estimated based on this data with the SES (that is poor and non-poor) as the dependent variable and a set of demographic variables as the explanatory variables. The results presented in this paper suggest that the DHS data can be used to determine the correlates of poverty.