Sample selection in the estimation of air bag and seat belt effectiveness

Because data are collected for only fatal crashes, it is difficult to accur ately measure seat belt and air bag effectiveness. The use of safety device s influences survival rates which in turn determine whether a crash is incl uded in the sample, leading to sample selection bias, We propose a simple s olution to the selection problem: limiting the sample to crashes in which s omeone in a different vehicle dies. Empirically, we find seat belts more ef fective and air bags to be less effective than previously found. The cost p er life saved through seat belts is approximately $30,000, compared to $1.8 million for air bags.