Doing More When You're Running LATE: Applying Marginal Treatment Effect Methods to Examine Treatment Effect Heterogeneity in Experiments

Kowalski, Amanda

doi:10.3386/w22363

Cited by 56 publications

(101 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…23 Recent work highlights that the relationship between insurance and ED use is likely complex and may vary based on the characteristics of the population covered, the nature of the insurance for the newly covered, and the availability of care for the uninsured, among other factors. 20,39 Methodological differences may also be a factor.…”

Section: Discussionmentioning

confidence: 99%

The Uninsured Do Not Use The Emergency Department More—They Use Other Care Less

et al. 2017

View full text Add to dashboard Cite

There is a popular perception that insurance coverage will reduce overuse of the emergency department (ED). Both opponents and advocates of expanding insurance coverage under the Affordable Care Act (ACA) have made statements to the effect that EDs have been jammed with the uninsured and that paying for the uninsured population’s emergency care has burdened the health care system as a result of the expense of that care. It has therefore been surprising to many to encounter evidence that insurance coverage increases ED use instead of decreasing it. Two facts may help explain this unexpected finding. First, there is a common misperception that the uninsured use the ED more than the insured. In fact, insured and uninsured adults use the ED at very similar rates and in very similar circumstances—and the uninsured use the ED substantially less than the Medicaid population. Second, while the uninsured do not use the ED more than the insured, they do use other types of care much less than the insured.

show abstract

Section: Discussionmentioning

confidence: 99%

The Uninsured Do Not Use The Emergency Department More—They Use Other Care Less

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Brinch, Mogstad, and Wiswall (forthcoming) show that a discrete instrument can be used to identify marginal treatment effects using functional form assumptions. Kowalski (2016) similarly shows that it is possible to bound and estimate average treatment effects for always takers and never takers using functional form assumptions. Most recently, Mogstad, Santos, and Torgovitsky (2017) show that because a LATE generally places some restrictions on unknown marginal treatment effects, it is possible to recover information about other estimands of interest.…”

mentioning

confidence: 95%

Racial Bias in Bail Decisions*

Arnold

Dobbie

Yang

2018

The Quarterly Journal of Economics

272

View full text Add to dashboard Cite

Silver, Alex Torgovitsky, and numerous seminar participants for helpful comments and suggestions. Molly Bunke, Kevin DeLuca, and Amy Wickett provided excellent research assistance. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research. NBER working papers are circulated for discussion and comment purposes. They have not been peer-reviewed or been subject to the review by the NBER Board of Directors that accompanies official NBER publications.

show abstract

“…A leading example concerns settings with instrumental variables (for example, Angrist 2004;Angrist and Fernandez-Val 2010;Dong and Lewbel 2015;Angrist and Rokkanen 2015;Bertanha and Imbens 2014;Kowalski 2016;Brinch, Mogstad, and Wiswall 2015). An instrumental variables estimator is often interpreted as an estimator of the local average treatment effect, that is, the average effect of the treatment for individuals whose treatment status is affected by the instrument.…”

Section: External Validitymentioning

confidence: 99%

The State of Applied Econometrics: Causality and Policy Evaluation

Athey

Imbens

2017

Journal of Economic Perspectives

994

518

View full text Add to dashboard Cite

The gold standard for drawing inferences about the effect of a policy is a randomized controlled experiment. However, in many cases, experiments remain difficult or impossible to implement, for financial, political, or ethical reasons, or because the population of interest is too small. For example, it would be unethical to prevent potential students from attending college in order to study the causal effect of college attendance on labor market experiences, and politically infeasible to study the effect of the minimum wage by randomly assigning minimum wage policies to states. Thus, a large share of the empirical work in economics about policy questions relies on observational data-that is, data where policies were determined in a way other than through random assignment. Drawing inferences about the causal effect of a policy from observational data is quite challenging. To understand the challenges, consider the example of the minimum wage. A naive analysis of the observational data might compare the average employment level of states with a high minimum wage to that of states with a low minimum wage. This difference is surely not a credible estimate of the causal effect of a higher minimum wage, defined as the change in employment that would occur if the low-wage states raised their minimum wage. For example, it might be the case that states with higher costs of living, as well as more price-insensitive consumers, choose higher levels of the minimum wage

show abstract

Doing More When You're Running LATE: Applying Marginal Treatment Effect Methods to Examine Treatment Effect Heterogeneity in Experiments

Cited by 56 publications

References 17 publications

The Uninsured Do Not Use The Emergency Department More—They Use Other Care Less

The Uninsured Do Not Use The Emergency Department More—They Use Other Care Less

Racial Bias in Bail Decisions*

The State of Applied Econometrics: Causality and Policy Evaluation

Contact Info

Product

Resources

About