Job Market Paper

From One LATE to Another: Machine Learning and the External Validity of IV Estimates

with Alexander Kwon

Interactive results

Presentations: 2027 ASSA Conference (poster) · 2026 Africa Meeting of the Econometric Society (presented by coauthor) · 2026 ASSA Conference (poster)

Abstract

Instrumental variable (IV) estimates identify local average treatment effects (LATEs) for compliers, whose composition can differ across populations. We study when a LATE estimated in a sample population can predict the LATE in a target population. We decompose the prediction error of the benchmark model, interacted two-stage least squares (I2SLS), into four terms and study which terms a more flexible model, Double/Debiased Machine Learning (DML), can reduce. Among them, we show that terms related to nonlinearity in the instrument propensity and outcome equations are significantly reduced by DML, but two terms, one related to the nonlinearity of the Conditional Average Treatment Effect and the other related to compliance weights, are not. We find that this decomposition is important because the overall prediction error can be small even when the individual terms are large, as they can cancel each other out due to differences in their signs. We apply these results in two Monte Carlo simulations, including one calibrated to data, and find supporting evidence.

Publications

External Validity in an Instrumental Variable Setting

with Alexander Kwon · Evaluation Review, 2025

Presentations: 2025 ASSA Conference (Lightning Session)

Abstract

We study external validity within the context of instrumental variable estimation. The key assumption we impose for external validity is conditional external unconfoundedness among compliers, which means that the treatment effect and target selection are independent among compliers conditional on covariates. We study this assumption by using a case study about the impact of solid fuel usage on women’s average cooking time. Among the six countries examined, we find no statistical evidence that the assumptions for external validity are violated for four countries (Ethiopia, Honduras, Kenya, and Zambia). Conversely, in Cambodia and Nepal, we find low external validity. These results provide suggestive evidence that the assumptions for external validity are violated for these two countries.

Geographical Factors Influencing Household Cookstove Choices in Nepal

with Alexander Kwon · Social Sciences & Humanities Open, 2025

Abstract

Using data from the Multi-Tier Framework Survey (MTF) conducted in Nepal, we explore how geographical factors, specifically land slope and elevation, impact the adoption of LPG stoves. We employ a logit model to analyze the factors influencing households’ choices regarding LPG stove adoption and generate slope and elevation data. Overall, we find that the estimates of the average slope are robust and statistically significant, but those for the average elevation are sensitive to model specifications and smaller compared to the slope. We find that the Kathmandu region is important in the analysis, and slope and elevation have nonlinear effects. Additionally, we show that geographical factors are similarly important across different household expenditure quintile groups, except for the lowest.

Working Papers

Clean Energy Access and Home Production Improvement: Labor Supply and Gender Difference

Draft available upon request.

Presentations: IAEE session, 2026 ASSA Conference · 2025 USAEE/IAEE North American Conference (Top 4 Finalist, Dennis J. O'Brien Best Student Paper Award)

Abstract

This paper examines how improvements in home production technology influence labor supply and time allocation within households. Using nationally representative data from Nepal, I estimate the causal impact of adopting liquefied petroleum gas (LPG) cookstoves, a cleaner and more efficient technology, on men’s and women’s labor market outcomes. To address endogeneity in stove adoption, I exploit geographic variation in average land slope as an instrumental variable that affects the cost and accessibility of LPG distribution but is otherwise unrelated to labor supply. The results show gender differences in response to the LPG stove adoption. LPG adoption increases men’s likelihood of employment and the number of workdays per year, while women’s employment and workdays decline modestly. On average, men work about 20 additional days per year following adoption, whereas women work about 20 fewer days per year. Time-use data indicate that LPG stoves substantially reduce time spent on fuel collection and cooking for both genders. Women reallocate much of this saved time to other domestic or caregiving tasks rather than market work. These findings provide empirical evidence that men and women respond differently to improvements in home production due to gender norms, labor-demand-side inequality, and intra-household bargaining power dynamics.

Work in Progress

Carbon Pricing and Heterogeneous Abatement Responses: Evidence from Seven U.S. Cities

with Jun Yoo

The Role of Accessibility in the Adoption of Clean Energy Stoves

with Nadia Doytch