Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning

Proxy means test (PMT) poverty targeting tools have become common tools for beneficiary targeting and poverty assessment where full means tests are costly. Currently popular estimation procedures for generating these tools prioritize minimization o...

Full description

Bibliographic Details
Main Authors:	McBride, Linden, Nichols, Austin
Format:	Working Paper
Language:	English en_US
Published:	World Bank, Washington, DC 2016
Subjects:	targeting proxy means testing poverty poverty assessment
Online Access:	http://documents.worldbank.org/curated/en/2016/10/26839841/retooling-poverty-targeting-using-out-of-sample-validation-machine-learning http://hdl.handle.net/10986/25166

id	okr-10986-25166
recordtype	oai_dc
spelling	okr-10986-251662021-04-23T14:04:29Z Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning McBride, Linden Nichols, Austin targeting proxy means testing poverty poverty assessment Proxy means test (PMT) poverty targeting tools have become common tools for beneficiary targeting and poverty assessment where full means tests are costly. Currently popular estimation procedures for generating these tools prioritize minimization of in-sample prediction errors; however, the objective in generating such tools is out-of-sample prediction. This paper presents evidence that prioritizing minimal out-of-sample error, identified through cross-validation and stochastic ensemble methods, in PMT tool development can substantially improve the out-of-sample performance of these targeting tools. The USAID poverty assessment tool and base data are used for demonstration of these methods; however, the methods applied in this paper should be considered for PMT and other poverty-targeting tool development more broadly. 2016-10-17T16:26:07Z 2016-10-17T16:26:07Z 2016-10 Working Paper http://documents.worldbank.org/curated/en/2016/10/26839841/retooling-poverty-targeting-using-out-of-sample-validation-machine-learning http://hdl.handle.net/10986/25166 English en_US Policy Research Working Paper;No. 7849 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo/ World Bank World Bank, Washington, DC Publications & Research Publications & Research :: Policy Research Working Paper
repository_type	Digital Repository
institution_category	Foreign Institution
institution	Digital Repositories
building	World Bank Open Knowledge Repository
collection	World Bank
language	English en_US
topic	targeting proxy means testing poverty poverty assessment
spellingShingle	targeting proxy means testing poverty poverty assessment McBride, Linden Nichols, Austin Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning
relation	Policy Research Working Paper;No. 7849
description	Proxy means test (PMT) poverty targeting tools have become common tools for beneficiary targeting and poverty assessment where full means tests are costly. Currently popular estimation procedures for generating these tools prioritize minimization of in-sample prediction errors; however, the objective in generating such tools is out-of-sample prediction. This paper presents evidence that prioritizing minimal out-of-sample error, identified through cross-validation and stochastic ensemble methods, in PMT tool development can substantially improve the out-of-sample performance of these targeting tools. The USAID poverty assessment tool and base data are used for demonstration of these methods; however, the methods applied in this paper should be considered for PMT and other poverty-targeting tool development more broadly.
format	Working Paper
author	McBride, Linden Nichols, Austin
author_facet	McBride, Linden Nichols, Austin
author_sort	McBride, Linden
title	Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning
title_short	Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning
title_full	Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning
title_fullStr	Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning
title_full_unstemmed	Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning
title_sort	retooling poverty targeting using out-of-sample validation and machine learning
publisher	World Bank, Washington, DC
publishDate	2016
url	http://documents.worldbank.org/curated/en/2016/10/26839841/retooling-poverty-targeting-using-out-of-sample-validation-machine-learning http://hdl.handle.net/10986/25166
_version_	1764458719900336128

Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning

Similar Items