Developing a Poverty Measurement Scorecard: Predicting MPCE for Microfinance Clients in Urban Delhi

Abstract

A scorecard is a poverty measurement tool (PMT) that helps microfinance institutions (MFI) to measure and track the poverty status of their clients. It uses some verifiable indicators from the national expenditure survey, to get a score that is highly correlated with poverty. In the present study, an attempt has been made to develop a scorecard using the stepwise OLS regression method, to predict the MPCE of MFI’s clients. The NSS 68th round (2011-12) data on consumption expenditure for urban Delhi has been used for this purpose. The predictive accuracy of the regression model (scorecard) is assessed by comparing the poverty status predicted by our scorecard with the “true” poverty status as established by the NSSO data. The “Total Accuracy” criterion is used which identified 89.39% of the respondents correctly. Thus, the scorecard appears to be a fairly accurate tool for assessing the poverty status of MFI’s clients.