Nowcasting Global Poverty
This paper evaluates different methods for nowcasting country-level poverty rates, including methods that apply statistical learning to large-scale country-level data obtained from the World Development Indicators and Google Earth Engine. The methods are evaluated by withholding measured poverty rates and determining how accurately the methods predict the held-out data. A simple approach that scales the last observed welfare distribution by a fraction of real GDP per capita growth—a method that departs slightly from current World Bank practice—performs nearly as well as models using statistical learning on 1,000+ variables. This GDP-based approach outperforms all models that predict poverty rates directly, even when the last survey is up to five years old. The results indicate that in this context, the additional complexity introduced by applying statistical learning techniques to a large set of variables yields only marginal improvements in accuracy.
Main Authors: | , , |
---|---|
Format: | Working Paper biblioteca |
Language: | English |
Published: |
World Bank, Washington, DC
2021-11
|
Subjects: | POVERTY, NOWCASTING, MACHINE LEARNING, POVERTY MEASUREMENT, |
Online Access: | http://documents.worldbank.org/curated/undefined/143231637760743360/Nowcasting-Global-Poverty http://hdl.handle.net/10986/36636 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-okr-1098636636 |
---|---|
record_format |
koha |
spelling |
dig-okr-10986366362021-12-03T05:10:41Z Nowcasting Global Poverty Mahler, Daniel Gerszon Castaneda Aguilar, R. Andres Newhouse, David POVERTY NOWCASTING MACHINE LEARNING POVERTY MEASUREMENT This paper evaluates different methods for nowcasting country-level poverty rates, including methods that apply statistical learning to large-scale country-level data obtained from the World Development Indicators and Google Earth Engine. The methods are evaluated by withholding measured poverty rates and determining how accurately the methods predict the held-out data. A simple approach that scales the last observed welfare distribution by a fraction of real GDP per capita growth—a method that departs slightly from current World Bank practice—performs nearly as well as models using statistical learning on 1,000+ variables. This GDP-based approach outperforms all models that predict poverty rates directly, even when the last survey is up to five years old. The results indicate that in this context, the additional complexity introduced by applying statistical learning techniques to a large set of variables yields only marginal improvements in accuracy. 2021-12-02T21:21:08Z 2021-12-02T21:21:08Z 2021-11 Working Paper http://documents.worldbank.org/curated/undefined/143231637760743360/Nowcasting-Global-Poverty http://hdl.handle.net/10986/36636 English Policy Research Working Paper;No. 9860 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 |
institution |
Banco Mundial |
collection |
DSpace |
country |
Estados Unidos |
countrycode |
US |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-okr |
tag |
biblioteca |
region |
America del Norte |
libraryname |
Biblioteca del Banco Mundial |
language |
English |
topic |
POVERTY NOWCASTING MACHINE LEARNING POVERTY MEASUREMENT POVERTY NOWCASTING MACHINE LEARNING POVERTY MEASUREMENT |
spellingShingle |
POVERTY NOWCASTING MACHINE LEARNING POVERTY MEASUREMENT POVERTY NOWCASTING MACHINE LEARNING POVERTY MEASUREMENT Mahler, Daniel Gerszon Castaneda Aguilar, R. Andres Newhouse, David Nowcasting Global Poverty |
description |
This paper evaluates different
methods for nowcasting country-level poverty rates,
including methods that apply statistical learning to
large-scale country-level data obtained from the World
Development Indicators and Google Earth Engine. The methods
are evaluated by withholding measured poverty rates and
determining how accurately the methods predict the held-out
data. A simple approach that scales the last observed
welfare distribution by a fraction of real GDP per capita
growth—a method that departs slightly from current World
Bank practice—performs nearly as well as models using
statistical learning on 1,000+ variables. This GDP-based
approach outperforms all models that predict poverty rates
directly, even when the last survey is up to five years old.
The results indicate that in this context, the additional
complexity introduced by applying statistical learning
techniques to a large set of variables yields only marginal
improvements in accuracy. |
format |
Working Paper |
topic_facet |
POVERTY NOWCASTING MACHINE LEARNING POVERTY MEASUREMENT |
author |
Mahler, Daniel Gerszon Castaneda Aguilar, R. Andres Newhouse, David |
author_facet |
Mahler, Daniel Gerszon Castaneda Aguilar, R. Andres Newhouse, David |
author_sort |
Mahler, Daniel Gerszon |
title |
Nowcasting Global Poverty |
title_short |
Nowcasting Global Poverty |
title_full |
Nowcasting Global Poverty |
title_fullStr |
Nowcasting Global Poverty |
title_full_unstemmed |
Nowcasting Global Poverty |
title_sort |
nowcasting global poverty |
publisher |
World Bank, Washington, DC |
publishDate |
2021-11 |
url |
http://documents.worldbank.org/curated/undefined/143231637760743360/Nowcasting-Global-Poverty http://hdl.handle.net/10986/36636 |
work_keys_str_mv |
AT mahlerdanielgerszon nowcastingglobalpoverty AT castanedaaguilarrandres nowcastingglobalpoverty AT newhousedavid nowcastingglobalpoverty |
_version_ |
1756576010682236928 |