I am a PhD candidate at MIT. I am interested in health economics and applied econometrics, and will be available for interviews for the 2022-2023 job market.

Click here for my CV, and here for my research statement.

Contact Information


Phone: 510-520-9675


PhD in Economics, 2023 (expected)

Massachusetts Institute of Technology

BA in Economics, Applied Mathematics, and Statistics, 2016

University of California, Berkeley

Working Papers

This paper studies consumers' demand for quality in the nursing home market, where information frictions are a source of concern. Using administrative data on the universe of nursing home residents, I estimate quality of nursing homes in California, and use these estimates as inputs into a structural demand model. I find substantial variation in nursing home quality: one standard deviation higher quality is associated with 2 percent lower risk-adjusted 90-day mortality rate. Yet, despite the high stakes for residents, average demand for quality is very low, even after accounting for unobserved supply-side constraints arising from selective admissions practices by nursing homes. Patterns of demand heterogeneity highlight information frictions as a major reason for this low demand: residents who were younger, highly educated, free from dementia, and who made their choices after the introduction of the star rating system were more responsive to quality. Counterfactual simulations based on estimates of the structural demand model and a competing risks model suggest that eliminating information frictions can reduce deaths by at least 8 to 28 percent, and potentially even more if supply side responses are considered.

Research in Progress

Assessing the Relative Importance and Potential Interactions Between Common Explanations for Racial Segregation: Evidence from Nursing Homes

Racial segregation is a pervasive phenomenon in a number of important settings, such as school, neighborhood, and nursing home choice. Past work has found evidence supporting a number of explanations for these patterns, including in-group preferences, discrimination, and location. However, since most of these factors have been studied independently, it is difficult to make precise statements about the relative importance of these explanations and potential interactions between them. In this project, I take advantage of an administrative data set on the universe of nursing home residents to study a number of explanations simultaneously using a two-sided matching model. The estimation results indicate that both in-group preferences and discrimination contribute to the observed pattern of minorities being disproportionately concentrated in lower-quality nursing homes, whereas location is unlikely to play a major role. Moreover, lower minority demand for quality also contributes to segregation, with further analysis suggesting that this may be due to information frictions. In simulations, I quantify the relative importance and potential interactions between these factors.

Selective Admissions and Discharges by Nursing Homes

Previous research has shown that as a consequence of capacity constraints, nursing homes selectively choose which types of residents to admit (Gandhi, 2019; Cheng, 2022), and when to discharge residents (Hackmann, Pohl, and Ziebarth, 2020). I provide a microfoundation for a structural model where arrivals of different types of potential residents and the evolution of “discharge readiness” of existing residents follow certain stochastic processes, and nursing homes choose optimal optimal admission and discharge policies that maximize expected present discounted value of future profits. The solution to this problem yields testable implications, and shed light on identification of the structural model – intuitively, nursing homes’ admission and discharge policies are identified by differences in the characteristics of residents they admit and discharge during times of high and low occupancy. I estimate the model using an extension of the Gibbs sampler in Agarwal and Somaini (2022) and Cheng (2022), with data augmentation on residents’ indirect utility and latent variables that determine nursing homes’ admission decisions for potential residents and discharge decisions for existing residents.

Bounds on Omitted Variables Bias in Discrete Choice Models

In this project, I extend methods in Altonji, Elder, and Taber (2005), and Oster (2019) for bounding omitted variables (OVB) bias in OLS to discrete choice settings. I derive bounds for the bias based on movements in the coefficient of interest before and after the inclusion of additional regressors, combined with an assumption about the importance of the omitted variables for consumer utility, relative to the importance of the additional regressors. I evaluate the robustness of this bounding procedure to alternative functional form assumptions using simulations. Finally, I conduct an empirical application studying whether the low estimates of nursing home residents’ demand for quality in Cheng (2022) can be explained by OVB. The bounds derived in this paper indicate that the gap between estimated demand for quality and demand estimates from the literature from other healthcare settings can only be explained by OVB if (i) residents value the omitted variable positively, but the omitted variable is negatively correlated with the main quality measure, and (ii) residents value the omitted variables at least 10 times more than they value publicly observable nursing home characteristics.

Past Work

Regression Discontinuity Designs with Multiple Running Variables [R Code]
In this paper, I introduce a new estimator for regression discontinuity designs with multiple running variables. My estimator provides efficiency gains relative to the common empirical practice of analyzing each running variable separately. In addition, it can be used to estimate heterogeneous treatment effects over a subset of the running variable space. I derive Bayesian confidence intervals for my estimator, and confirm their validity in simulations. Finally, I demonstrate the performance of my estimator in an empirical application from Londoño-Vélez, Rodríguez, and Sánchez (2020), which studies the effect of a large financial aid program on higher education in Colombia.

Cigarette Consumption and Tax Salience
This paper studies how cigarette consumption responds over time to changes in tax rates. Using a panel of state data, I estimate that the cumulative effect of an excise tax rise on consumption is larger than the cumulative effect of an increase in sales tax, in line with a theory of tax salience. In addition, I find that consumption falls in advance of an excise tax hike, whereas it only falls in the year after a sales tax increase. The pattern of consumption response to sales taxes is also consistent with consumer learning over time.

Does Fake News Affect Voting Behavior? (Slides)
The issue of fake news has been hotly debated since the 2016 election, and there is a perception among many that fake news played a key role in Trump’s election victory. Despite these claims, there has been limited evidence to date on the extent to which fake news affects voting behavior. In this project, I seek to provide credible evidence on this question by using big college football games as an instrument for fake news consumption. I find that search volumes for pro-Trump fake news terms were lower in counties close to college football teams that played a big game shortly before the election, and also that these counties were less likely to vote for Trump. The magnitude of these estimates suggest that a one-standard deviation increase in search volume for pro-Trump fake news terms increased Trump’s vote share by about 5 percent. Finally, I do not find evidence that fake news affected overall turnout rates, or that fake news resulted in down-ballot effects.