National Bureau of Economic Research Working PapersThe Latest NBER Working Papers
http://www.nber.org/new.html
An Empirical Model of the Medical Match -- by Nikhil AgarwalThis paper develops a framework for estimating preferences in two-sided matching markets with non-transferable utility using only data on observed matches. Unlike single-agent choices, matches depend on the preferences of other agents in the market. I use pairwise stability together with a vertical preference restriction on one side of the market to identify preference parameters for both sides of the market. Recovering the distribution of preferences is only possible in an environment with many-to-one matching. These methods allow me to investigate two issues concerning the centralized market for medical residents. First, I examine the antitrust allegation that the clearinghouse restrains competition, resulting in salaries below the marginal product of labor. Counterfactual simulations of a competitive wage equilibrium show that residents' willingness to pay for desirable programs results in estimated salary markdowns ranging from $23,000 to $43,000 below the marginal product of labor, with larger markdowns at more desirable programs. Therefore, a limited number of positions at high quality programs, not the design of the match, is the likely cause of low salaries. Second, I analyze wage and supply policies aimed at increasing the number of residents training in rural areas while accounting for general equilibrium effects from the matching market. I find that financial incentives increase the quality, but not the number of rural residents. Quantity regulations increase the number of rural trainees, but the impact on resident quality depends on the design of the intervention.
http://papers.nber.org/papers/w20767#fromrss
http://papers.nber.org/papers/w20767#fromrssExternal Validity in Fuzzy Regression Discontinuity Designs -- by Marinho Bertanha, Guido W. ImbensMany empirical studies use Fuzzy Regression Discontinuity (FRD) designs to identify treatment effects when the receipt of treatment is potentially correlated to outcomes. Existing FRD methods identify the local average treatment effect (LATE) on the subpopulation of compliers with values of the forcing variable that are equal to the threshold. We develop methods that assess the plausibility of generalizing LATE to subpopulations other than compliers, and to subpopulations other than those with forcing variable equal to the threshold. Specifically, we focus on testing the equality of the distributions of potential outcomes for treated compliers and always-takers, and for non-treated compliers and never-takers. We show that equality of these pairs of distributions implies that the expected outcome conditional on the forcing variable and the treatment status is continuous in the forcing variable at the threshold, for each of the two treatment regimes. As a matter of routine, we recommend that researchers present graphs with estimates of these two conditional expectations in addition to graphs with estimates of the expected outcome conditional on the forcing variable alone. We illustrate our methods using data on the academic performance of students attending the summer school program in two large school districts in the US.
http://papers.nber.org/papers/w20773#fromrss
http://papers.nber.org/papers/w20773#fromrss