In an ongoing evaluation of post-secondary financial aid, we use random assignment to assess the causal effects of large privately-funded aid awards. Here, we compare the unbiased causal effect estimates from our RCT with two types of non-experimental econometric estimates. The first applies a selection-on-observables assumption in data from an earlier, nonrandomized cohort; the second uses a regression discontinuity design. Selection-on-observables methods generate estimates well below the experimental benchmark. Regression discontinuity estimates are similar to experimental estimates for students near the cutoff, but sensitive to controlling for the running variable, which is unusually coarse.

This Job Is "Getting Old": Measuring Changes in Job Opportunities Using Occupational Age Structure by David Autor and David Dorn. Published in volume 99, issue 2, pages 45-51 of American Economic Review, May 2009

We offer a unified analysis of the growth of low-skill service occupations between 1980 and 2005 and the concurrent polarization of US employment and wages. We hypothesize that polarization stems from the interaction between consumer preferences, which favor variety over specialization, and the falling cost of automating routine, codifiable job tasks. Applying a spatial equilibrium model, we corroborate four implications of this hypothesis. Local labor markets that specialized in routine tasks differentially adopted information technology, reallocated low-skill labor into service occupations (employment polarization), experienced earnings growth at the tails of the distribution (wage polarization), and received inflows of skilled labor.

The Employment Consequences of Wrongful-Discharge Laws: Large, Small, or None at All? by David H. Autor, John J. Donohue and Stewart J. Schwab. Published in volume 94, issue 2, pages 440-446 of American Economic Review, May 2004

A set of studies conducted over the last 15 years has produced a near consensus that the Social Security Disability Insurance system (SSDI) has substantial disincentive effects on the labor supply of near elderly males, diminishing labor force participation, increasing the sensitivity of labor force exit decisions to adverse economic shocks, and encouraging those nearing retirement to claim disability benefits and subsequently transfer into the Social Security retirement program. Yet, efforts by the Social Security Administration (SSA) to encourage labor supply among the disabled by removing the work disincentives built into SSDI have been almost entirely unsuccessful. Most notably, in 1999, Congress authorized the Ticket to Work program, which provides an array of inducements for current SSDI beneficiaries to take up employment, including permitting a trial work period of up to nine months, providing 7.75 years of ongoing Medicare eligibility following return to work, and providing three years of automatic benefit reinstatement when claimants’ workplace earnings fall below a threshold level. Each of these steps reduces the implicit tax placed on labor supply by the SSDI program. Despite these lures, fewer than 1,400 (0.01 percent) of the 12.2 million tickets issued to date have led to successful workforce integration (Autor and Duggan 2006).