A study released this month from the RAND Corporation sounds like good news for gun control advocates.
According to the study’s authors, the 18 states with the most restrictive child access, right-to-carry, and “stand-your-ground” laws experienced an 11 percent reduction in firearm deaths (homicides and suicides) between 1980 and 2016.
If these restrictive policies were implemented nationwide, the authors claim, the United States could see 4,475 fewer gun-related deaths each year.
“It appears that state policies restricting how people store, carry, and use their weapons are likely to have a small, but meaningful effect on reducing the number of firearm-related suicides and homicides in a state,” said Terry Schell, lead author of the study and a behavioral scientist at RAND, a nonprofit research organization.
There’s just one problem: the study is garbage.
“None of their results are statistically significant. This is not a serious paper,” Dr. John R. Lott, president of the Crime Prevention Research Center, told GunsAmerica.
Lott points to the confidence interval the authors use to analyze their data. The confidence interval is the likelihood that the true value (in this case, the effect of gun laws) lies within a certain range. To determine statistically significant results, most studies use a confidence interval between 95 and 99 percent, Lott says. This study uses a confidence interval of 80 percent.
“I have never previously seen a paper that uses 80 perfect confidence intervals,” Lott said. “It is clear that they did that because they wouldn’t have gotten any statistically significant results if they used 95% or even 90% confidence intervals.”
The authors make a number of other fallacious assumptions.
They assume, for example, that the impact of right-to-carry laws causes a large, immediate increase in the number of permits. But that is not the case, Lott said, because states differ widely on how they issue permits – even when they have shall-issue laws on the books.
Even the study’s authors admit that their analysis is flawed. They note in the final paragraphs of the paper that perpetrators of homicides and suicides may very well achieve the same outcomes by different means.
They also admit that they have no way of knowing whether their observations represent the causal effects of gun laws or the effects of other variables. In other words, even if a state sees a drop in gun-related homicides and suicides, gun policies might not be responsible for that drop.
So far, RAND’s study hasn’t garnered a lot of attention from the anti-gun lobby or the mainstream media. But you can bet that its limitations won’t stop them from reporting the top-line “results” without any of the limiting factors.