Small area estimation of non-monetary poverty with geospatial data

Abstract

This paper evaluates the benefits of combining household surveys with satellite and other geospatial data to generate small area estimates of non-monetary poverty. Using data from Tanzania and Sri Lanka and applying a household-level empirical best (EB) predictor mixed model, we find that combining survey data with geospatial data significantly improves both the precision and accuracy of our non-monetary poverty estimates. While the EB predictor model moderately underestimates standard errors of those point estimates, coverage rates are similar to standard survey-based standard errors that assume independent outcomes across clusters.