The sharp regression discontinuity design (RDD) has three key weaknesses compared to the randomized clinical trial (RCT). It has lower statistical power, it is more dependent on statistical modeling assumptions, and its treatment effect estimates are limited to the narrow subpopulation of cases immediately around the cutoff, which is rarely of…

This paper analyzes 12 recent within-study comparisons contrasting causal estimates from a randomized experiment with those from an observational study sharing the same treatment group. The aim is to test whether different causal estimates result when a counterfactual group is formed, either with or without random assignment, and when statistical…

This paper uses the widespread variation across states in the timing of adoption of tougher drunk driving laws that set very low legal blood alcohol limits for drivers under age 21--"zero tolerance" (ZT) laws--to provide new evidence on the causal effect of alcohol use on youth suicide. ZT laws reduced heavy episodic drinking by underage men, with…