Applications of econometrics and machine learning to development and international economics

• Main Author: Hersh, Jonathan Samuel
• Other Authors: Baxter, Marianne
• Language: en_US
• Published: 2019
• Subjects: Economics; Economic development; Machine learning; Poverty; Trade
• Online Access: https://hdl.handle.net/2144/33048

In the first chapter, I explore whether features derived from high resolution satellite images of Sri Lanka are able to predict poverty or income at local areas. I extract from satellite imagery area specific indicators of economic well-being including the number of cars, type and extent of crops, length and type of roads, roof extent and roof type, building height and number of buildings. Estimated models are able to explain between 60 to 65 percent of the village-specific variation in poverty and average level of log income. The second chapter investigates the effects of preferential trade programs such as the U.S. African Growth and Opportunity Act (AGOA) on the direction of African countries’ exports. While these programs intend to promote African exports, textbook models of trade suggest that such asymmetric tariff reductions could divert African exports from other destinations to the tariff reducing economy. I examine the import patterns of 177 countries and estimate the diversion effect using a triple-difference estimation strategy, which exploits time variation in the product and country coverage of AGOA. I find no evidence of systematic trade diversion within Africa, but do find evidence of diversion from other industrialized destinations, particularly for apparel products. In the third chapter I apply three model selection methods – Lasso regularized regression, Bayesian Model Averaging, and Extreme Bound Analysis -- to candidate variables in a gravity models of trade. I use a panel dataset of of 198 countries covering the years 1970 to 2000, and find model selection methods suggest many fewer variables are robust that those suggested by the null hypothesis rejection methodology from ordinary least squares.