On the estimation of fuzzy poverty indices using official survey data. Variance estimation, robustness and computational considerations

We review the fuzzy approach to poverty measurement by comparing poverty indices having different membership functions proposed in the literature. We simulate two sample surveys from EU-SILC data to examine the statistical properties, sampling errors and robustness to parameter specification of the fuzzy indices considered. Two traditional crisp-set poverty indices (Head Count Ratio and Poverty Gap) are also compared to highlight their close link to the fuzzy approach.