Drought-sensitive targeting and child growth faltering in Southern Africa
Javier Baez,
Varun Kshirsagar and
Emmanuel Skoufias
World Development, 2024, vol. 182, issue C
Abstract:
We combine remote-sensed data and individual child, mother, and household level data for five countries in Sub-Saharan Africa (Malawi, Tanzania, Mozambique, Zambia, and Zimbabwe) to design a prototype drought-sensitive targeting framework that may be used in scarce-data contexts. To accomplish this we: i) develop simple and easy-to-communicate measures of drought shocks; ii) show that droughts have a large impact on child growth faltering in these five countries -- comparable, in size, to the effects of mother’s illiteracy, living in a house with a primitive roof, or to a fall to a lower wealth quintile; and iii) show that, in this context, decision trees and regressions predict growth faltering as accurately (out-of-sample) as machine learning methods that are not interpretable. Taken together, our analysis lends support to the idea that a data-driven targeting approach may contribute to the design of policies that alleviate the impact that climate change has on the world’s most vulnerable populations.
Keywords: Poverty; Child Welfare; Climate change; Poverty targeting; Social Protection; Child Malnourishment; Interpretable Machine Learning (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0305750X24001724
Full text for ScienceDirect subscribers only
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:eee:wdevel:v:182:y:2024:i:c:s0305750x24001724
DOI: 10.1016/j.worlddev.2024.106702
Access Statistics for this article
World Development is currently edited by O. T. Coomes
More articles in World Development from Elsevier
Bibliographic data for series maintained by Catherine Liu ().