EVENT:

On October 24th, 2017, the AidData-hosted event, Tyranny of Averages: Are we worsening inequality within countries?, brought together Amanda Glassman (CGD), Caroline Heider (World Bank), Selim Jahan (UNDP), Kevin Croke (World Bank), Bradley C. Parks (AidData) and Samantha Custer (AidData) for an engaging panel discussion on issues of inequality and aid targeting addressed by the report. Watch the recording or read a summary of the remarks.

Journal Article

Quantifying Heterogeneous Causal Treatment Effects in World Bank Development Finance Projects

Date Published

Dec 30, 2017

Authors

Jianing Zhao, Daniel M. Runfola, Peter Kemper

Publisher

Citation

Zhao J., Runfola D.M., Kemper P. (2017) Quantifying Heterogeneous Causal Treatment Effects in World Bank Development Finance Projects. In: Altun Y. et al. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2017. Lecture Notes in Computer Science, vol 10536. Springer, Cham

Update: A revised version of this paper has been published in Health Economics.

Journal Article

Quantifying Heterogeneous Causal Treatment Effects in World Bank Development Finance Projects

Date Published

Dec 30, 2017

Authors

Jianing Zhao, Daniel M. Runfola, Peter Kemper

Citation

Zhao J., Runfola D.M., Kemper P. (2017) Quantifying Heterogeneous Causal Treatment Effects in World Bank Development Finance Projects. In: Altun Y. et al. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2017. Lecture Notes in Computer Science, vol 10536. Springer, Cham

The World Bank provides billions of dollars in development finance to countries across the world every year. As many projects are related to the environment, we want to understand the World Bank projects impact to forest cover. However, the global extent of these projects results in substantial heterogeneity in impacts due to geographic, cultural, and other factors. Recent research by Athey and Imbens has illustrated the potential for hybrid machine learning and causal inferential techniques which may be able to capture such heterogeneity. We apply their approach using a geolocated dataset of World Bank projects, and augment this data with satellite-retrieved characteristics of their geographic context (including temperature, precipitation, slope, distance to urban areas, and many others). We use this information in conjunction with causal tree (CT) and causal forest (CF) approaches to contrast ÔcontrolÕ and ÔtreatmentÕ geographic locations to estimate the impact of World Bank projects on vegetative cover.

Related Publications

No items found.
Tags
Available on GeoQuery
TUFF
Geocoded
SDG Coded
Natural Resource Concessions
Survey Results
Metadata
Publication Date
Mar 2017
Starting Year:
1995
Ending Year:
2014
Number of Entries:
61,243
File Size:

This is all projects approved from 1995-2014 of the World Bank IBRD/IDA lending lines. This dataset tracks 5684 geocoded projects across 61243 locations, $630,187,678,017.21 in geocoded commitments and $389,037,095,461.60 in geocoded disbursements.

Related Posts

No items found.