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 performs nearly as well as models using statistical learning on 1,000 plus 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: | Journal Article biblioteca |
Language: | English en_US |
Published: |
Published by Oxford University Press on behalf of the World Bank
2022-10-06
|
Subjects: | POVERTY, NOWCASTING, MACHINE LEARNING, MEASUREMENT, |
Online Access: | http://documents.worldbank.org/curated/en/099658312112338950/IDU0519867a504b6f04e4c0bf3d0e3b9b7b70d3b https://hdl.handle.net/10986/41135 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-okr-1098641135 |
---|---|
record_format |
koha |
spelling |
dig-okr-10986411352024-03-26T15:51:34Z Nowcasting Global Poverty Mahler, Daniel Gerszon Aguilar, R. Andrés Castañeda Newhouse, David POVERTY NOWCASTING MACHINE LEARNING 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 performs nearly as well as models using statistical learning on 1,000 plus 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. 2024-02-29T19:38:40Z 2024-02-29T19:38:40Z 2022-10-06 Journal Article http://documents.worldbank.org/curated/en/099658312112338950/IDU0519867a504b6f04e4c0bf3d0e3b9b7b70d3b The World Bank Economic Review 0258-6770 (print) 1564-698X (online) https://hdl.handle.net/10986/41135 English en_US World Bank Economic Review The World Bank Economic Review CC BY-NC-ND 3.0 IGO http://creativecommons.org/licenses/by-nc-nd/3.0/igo World Bank application/pdf text/plain Published by Oxford University Press on behalf of the World Bank |
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 en_US |
topic |
POVERTY NOWCASTING MACHINE LEARNING MEASUREMENT POVERTY NOWCASTING MACHINE LEARNING MEASUREMENT |
spellingShingle |
POVERTY NOWCASTING MACHINE LEARNING MEASUREMENT POVERTY NOWCASTING MACHINE LEARNING MEASUREMENT Mahler, Daniel Gerszon Aguilar, R. Andrés Castañeda 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 performs nearly as well as models using statistical
learning on 1,000 plus 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 |
Journal Article |
topic_facet |
POVERTY NOWCASTING MACHINE LEARNING MEASUREMENT |
author |
Mahler, Daniel Gerszon Aguilar, R. Andrés Castañeda Newhouse, David |
author_facet |
Mahler, Daniel Gerszon Aguilar, R. Andrés Castañeda 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 |
Published by Oxford University Press on behalf of the World Bank |
publishDate |
2022-10-06 |
url |
http://documents.worldbank.org/curated/en/099658312112338950/IDU0519867a504b6f04e4c0bf3d0e3b9b7b70d3b https://hdl.handle.net/10986/41135 |
work_keys_str_mv |
AT mahlerdanielgerszon nowcastingglobalpoverty AT aguilarrandrescastaneda nowcastingglobalpoverty AT newhousedavid nowcastingglobalpoverty |
_version_ |
1794797140421115904 |