Adaptive Safety Nets for Rural Africa : Drought-Sensitive Targeting with Sparse Data

Baez, Javier E. ; Kshirsagar, Varun ; Skoufias, Emmanuel

World Bank, Washington, DC

关键词: SAFETY NETS;    POVERTY;    CHILD WELFARE;    CLIMATE CHANGE;    TARGETING;   

DOI  :  10.1596/1813-9450-9071
RP-ID  :  WPS9071

学科分类：社会科学、人文和艺术（综合）

来源: World Bank Open Knowledge Repository

【 摘 要 】

This paper combines remote-sensed dataand individual child-, mother-, and household-level datafrom the Demographic and Health Surveys for five countriesin Sub-Saharan Africa (Malawi, Tanzania, Mozambique, Zambia,and Zimbabwe) to design a prototype drought-contingenttargeting framework that may be used in scarce-datacontexts. To accomplish this, the paper: (i) develops simpleand easy-to-communicate measures of drought shocks; (ii)shows that droughts have a large impact on child stunting inthese five countries -- comparable, in size, to the effectsof mother's illiteracy and a fall to a lower wealthquintile; and (iii) shows that, in this context, decisiontrees and logistic regressions predict stunting asaccurately (out-of-sample) as machine learning methods thatare not interpretable. Taken together, the analysis lendssupport to the idea that a data-driven approach maycontribute to the design of policies that mitigate theimpact of climate change on the world's most vulnerable populations.