A new GLO Discussion Paper compares the performance of econometric and machine learning models in predicting poverty.
The Global Labor Organization (GLO) is an independent, non-partisan and non-governmental organization that functions as an international network and virtual platform to stimulate global research, debate and collaboration.
GLO Discussion Paper No. 468, 2020
GLO Fellow Paolo Verme
Author Abstract: OLS models are the predominant choice for poverty predictions in a variety of contexts such as proxy-means tests, poverty mapping or cross-survey imputations. This paper compares the performance of econometric and machine learning models in predicting poverty using alternative objective functions and stochastic dominance analysis based on coverage curves. It finds that the choice of an optimal model largely depends on the distribution of incomes and the poverty line. Comparing the performance of different econometric and machine learning models is therefore an important step in the process of optimizing poverty predictions and targeting ratios.
GLO Discussion Papers are research and policy papers of the GLO Network which are widely circulated to encourage discussion. Provided in cooperation with EconStor, a service of the ZBW – Leibniz Information Centre for Economics, GLO Discussion Papers are among others listed in RePEc (see IDEAS, EconPapers). Complete list of all GLO DPs – downloadable for free.