We investigate the effects of automobile congestion on ambient air pollution and local infant mortality rates using data from California spanning 2002 to 2007. Constructing instrumental variables (IV) using the relationship of traffic, weather conditions, and pollutants, we show that particulate matter, even at modern levels, has large marginal effects on weekly infant mortality rates, especially for premature or low birthweight infants. We also find suggestive evidence of large effects for carbon monoxide, though results are imprecise. Finally, we check estimate sensitivity to nonclassical measurement error in local pollution and show that our IV results are robust to such concerns.

Researchers have increasingly realized the need to account for within-group dependence in estimating standard errors of regression parameter estimates. The usual solution is to calculate cluster-robust standard errors that permit heteroskedasticity and within-cluster error correlation, but presume that the number of clusters is large. Standard asymptotic tests can over-reject, however, with few (five to thirty) clusters. We investigate inference using cluster bootstrap-t procedures that provide asymptotic refinement. These procedures are evaluated using Monte Carlos, including the example of Bertrand, Duflo, and Mullainathan (2004). Rejection rates of 10% using standard methods can be reduced to the nominal size of 5% using our methods.