Assessing Alternative Poverty Proxy Methods in Rural Vietnam

摘要: This paper compares and contrasts the use of four “short-cut” methods for identifying poor households: poverty probability method; ordinary least squares regressions; principal components analysis; quantile regressions. After evaluating these using two alternative criteria (total balanced accuracy) representative household survey data from rural Vietnam, it is concluded that method—which can correctly identify around four-fifths non-poor households—is most accurate method measuring specific subpopulations, or in years when surveys are not available. The performance was then tested with different lines an survey, found to be robust.