Incorporating Uncertainty in Poverty Dynamics: How Can We Assess the Economic Impact of Aids Mortality in the Presence of Measurement Error and Missing Data? Aids Mortality in the Presence of Measurement Error and Missing Data?

Abstract

The objective of this paper is twofold: it aims at evaluating the quality of the consumption module in the ACDIS data, addressing measurement error and missing information. Estimates of household consumption are in fact sensitive to both issues (Ardington, Lam et al. 2006). Secondly, it aims at assessing the extent to which contaminated data can affect poverty measures. This paper adopts a comprehensive approach to deal with defective data when measuring household welfare using consumption aggregates. The final aim is to produce poverty (or welfare) indicators for each socio-economic wave under various imputation scenarios. This research is instrumental to study the changes in consumption-poverty induced by AIDS mortality in Kwazulu-Natal.