POVERTY MAPPING AT SMALL AREA LEVEL IN PAKISTAN: A COMPARATIVE ANALYSIS OF ELL AND EXTENDED ELL METHODS

Abstract

This seminal research conducts a rigorous comparative analysis for the first time to determine the optimal methodology among the ELL (Elbers et al. 2003) and extended ELL (Nguyen et al. 2018) approaches to Small Area Estimation (SAE), ultimately identifying the most deprived districts in Pakistan. The statistically robust unit-level ELL and Extended ELL Methodologies are used under the Small Area Estimation (SAE) Technique to estimate poverty headcount based on the proportion of deprived households, utilizing the data from the Household Integrated Economic Survey (HIES) 2018-19 and the Pakistan Social and Living Standards Measurement Survey (PSLM) 2019-20. A comparison of Mean Squared Errors (MSE) of Poverty estimates via the ELL and Extended ELL methods reveals that the ELL method outperforms the Extended ELL method. Apart from the methodological superiority of the traditional ELL method, both methodologies unveil the presence of extreme poverty in 13 districts, 19 districts experiencing severe poverty, and finally 04 districts with moderate poverty but on the verge of severe poverty. This granular mapping of poverty intensity across districts provides invaluable insights for the Government and policymakers regarding the priority areas for intervention. It allows for the tailoring of poverty reduction strategies to the specific needs and circumstances of each deprived district in Pakistan.