John Lott’s newest piece at Fox News starts this way:
Between 1996 and 2013, 991 police officers have been killed in the line of duty. These public servants put their lives on the line to protect Americans. Their deaths should concern everyone, including public health researchers. But researchers’ dislike of guns may be clouding their judgment, and a new study, which claims that more police were feloniously killed in states with more guns, mistakenly concludes that private gun ownership causes police deaths.
The study, which was announced last week and is forthcoming in the American Journal of Public Health, received extensivenational and international news coverage. But if the researchers hadn’t left out controls used by everyone else for this type of empirical work, they would have gotten the opposite results from what they claimed.
Previous research has done just that. And it has found that concealed handgun permits lead to fewer police deaths. The authors offered no explanation for the new study’s unorthodox approach.
There is a big benefit to using so-called panel data, where you follow changes in crime rates across many different states over a number of years. Doing that allows you to have many different experiments and makes it possible to more accurately explain for differences in crime rates across states or over time.
A couple of simple examples show why other studies on crime take into account these factors.
Take a common comparison of different countries. As many people point out, the UK has both a lower gun ownership rate and a lower homicide rate than the US does. Yet, it does not logically follow that reducing gun ownership leads to a reduction in crime. And, in fact, after the UK’s 1997 nationwide handgun ban, their homicide rate actually increased by 50 percent over the next eight years. The UK still had a lower homicide rate than the US, but this wasn’t because of the handgun ban. Other factors must have played a role. The ban itself raised their homicide rate.
A similar point applies over time. . . . .
The rest of the piece is available here.