Estimating the effect of concealed carry laws on murder: A response to Bondy, et al.

Abstract

In 2021 we wrote a short paper noting that truncating the sample when estimating the effect of right to carry laws on crime could be biased by comparisons to states that already adopted the law, instead of states without the law. In 2023 Bondy et al. criticized our paper but inaccurately described what we did and provided selective and misleading results. More importantly, they completely missed the point of our analysis, namely that applying two-way fixed effects to a truncated sample, say 1991–2018, biases the resulting RTC coefficient by invalidly comparing newly treated states to 11 previously treated states. The bias is so large that even if the true coefficient on the right-to-carry dummy is negative, the estimated coefficient could be positive. These biased results can be corrected by using new DID estimators, that do not make invalid comparisons, and which are robust to time and state heterogeneity. Using these new estimators, we find that RTC laws do not significantly increase violent crime. We find evidence that RTC laws significantly reduce murder and that constitutional carry laws significantly reduce rape.