We exploit the structure of the Clean Air Act to provide new evidence on the capitalization of total suspended particulates (TSPs) air pollution into housing values. This legislation imposes strict regulations on polluters in “nonattainment” counties, which are defined by concentrations of TSPs that exceed a federally set ceiling. TSPs nonattainment status is associated with large reductions in TSPs pollution and increases in county‐level housing prices. When nonattainment status is used as an instrumental variable for TSPs, we find that the elasticity of housing values with respect to particulates concentrations ranges from −0.20 to −0.35. These estimates of the average marginal willingness to pay for clean air are robust to quasi‐experimental regression discontinuity and matching specification tests. Further, they are far less sensitive to model specification than cross‐sectional and fixed‐effects estimates, which occasionally have the “perverse” sign. We also find modest evidence that the marginal benefit of reductions of TSPs is lower in communities with relatively high pollution levels, which is consistent with preference‐based sorting. Overall, the improvements in air quality induced by the mid‐1970s TSPs nonattainment designation are associated with a $45 billion aggregate increase in housing values in nonattainment counties between 1970 and 1980.

Many programs reward or penalize schools based on students' average performance. Mean reversion is a potentially serious hindrance to the evaluation of such interventions. Chile's 900 Schools Program (P-900) allocated resources based on cutoffs in schools' mean test scores. This paper shows that transitory noise in average scores and mean reversion lead conventional estimation approaches to overstate the impacts of such programs. It further shows how a regressiondiscontinuity design can be used to control for reversion biases. It concludes that P-900 had significant effects on test score gains, albeit much smaller than is widely believed