We consider inference in regression discontinuity designs when the running variable only takes a moderate number of distinct values. In particular, we study the common practice of using confidence intervals (CIs) based on standard errors that are clustered by the running variable. We derive...

Currently there is little practical advice on which treatment effect estimator to use when trying to adjust for observable differences. A recent suggestion is to compare the performance of estimators in simulations that somehow mimic the empirical context. Two ways to run such 'empirical Monte...

This paper considers the semiparametric identification of endogenous and exogenous peer effects based on group size variation. We show that Lee (2006)'s linear-in-means model is generically identified, even when all members of the group are not observed. While unnecessary in general,...

This paper exploits the reduction in the legal drinking age in New Zealand from 20 to 18 to study the dynamics of youth risk taking. Using administrative data on the universe of road accidents over a fifteen year period spanning the law change, we undertake three complimentary analyses to...

We provide a framework to disentangle preferences and beliefs in health behavior and apply it to lockdown compliance in the UK. We estimate a model of compliance choice with uncertain costs and benefits to quantify utility tradeoffs, decompose group differences in compliance, and compute...

This paper examines the impact of a reduction in the legal drinking age in New Zealand from 20 to 18 on alcohol use, and alcohol-related hospitalisations and vehicular accidents among teenagers. We use both a difference-in-differences approach and a regression discontinuity design (RDD) to...

The maximum likelihood estimator for the regression coefficients, β, in a panel binary response model with fixed effects can be severely biased if N is large and T is small, a consequence of the incidental parameters problem. This has led to the development of conditional maximum likelihood...

Twenty-six states require that women seeking an abortion wait between 18 and 72 hours after receipt of counseling before the abortion can be completed. Thirteen states require that the counseling be given in person necessitating at least two visits to the provider. In April of 2015, Arkansas...

We find a strong relationship between risk-loving preferences and cognitive ability which becomes stronger as adherence to the generalized axiom of revealed preference (a proxy for rationality) increases. Our results are taken from a field study of individuals at the very bottom of the income...

We investigate behavioral responses to a staggered disruption in the supply of prescription opioids across U.S. states: the introduction of electronic Prescription Drug Monitoring Programs (PDMPs). Using administrative datasets, we find PDMPs curtail the proliferation of prescription opioids....