JOHN LOTT UPDATE: I've been slow to believe charges of dishonesty aimed at John Lott. First, I don't understand the underlying statistics well enough, and second, Lott has been the target of many vicious smears and lies, which tends to make me reflexively doubt the latest charges by his many antigun critics. (For example, because he had an Olin Fellowship at the University of Chicago, antigun people said his research was funded by Winchester, a company the Olin family, which endowed the fellowships, once owned -- which is sort of like saying that the Henry Luce Professor of Jurisprudence at Yale is "bought and paid for by Time Magazine." I don't think they ever apologized, either.)
Nonetheless, the question of coding errors in some of Lott's research, discussed earlier on InstaPundit here and here, continues to stand. John Donohue of Stanford sent me a letter to the editor, which he (together with Ian Ayres of Yale) sent in response to something from Lott. I asked him for permission to reprint it here (I got the idea from his email that he wanted me to, but I wasn't completely certain), and haven't heard back -- but I notice that Tim Lambert has already posted it.
While I suspect that Ayres and Donohue favor gun control, and dislike Lott's theories on policy grounds, I regard them as honest guys -- though I went to law school with them and may be biased thereby. At any rate, while I can't speak to the merits of the statistical argument myself, it is notable that Ayres and Donohue are now doing something that they have not done earlier, which is accusing Lott of being deliberately misleading, not of mere inadvertence. I expect that this debate isn't over.
It's also worth noting something that Mark Kleiman said earlier on this:
At the end of the day, though, it's pretty clear that if "shall-issue" increases gun violence at all, it doesn't do so by very much. To that limited extent, Lott was right and the gun controllers were wrong.
Given that anti-gun people predicted, over and over again, that the streets would be red with blood if shall-issue were adopted in various states, that's no small thing.
UPDATE: Lott phoned me -- he's away from computers but had heard of this post by phone. He emphatically denies any deception, says that he's made all the data available on his website, and promises to send me an email when he's online. He also says that the claim of a small increase in crime is wrong.
ANOTHER UPDATE: I want to be clear, here -- I think I was anyway, but after the Ashcroft thing my confidence is blown -- that neither Lambert, Ayres, or Donohue was behind the bogus "Winchester" claims. Those came from anti-gun groups, and were parroted by sympathetic politicians and journalists.
YET ANOTHER UPDATE: John Lott has posted a response on his website.