Friday, April 12, 2013

Background Checks and Murder Rates

The first draft of a law review article examining the evidence of what effect state mandatory firearms background check laws have on murder rates has been submitted to SSRN; if you don't know what SSRN is, see this article about it.  It may be a day or two before SSRN makes it visible.  I will be intermittently off the network over the next day or so, but as soon as I see it visible, I will let everyone know.  In the meantime, feel free to go here and search for articles by me.  If you see "Background Checks and Murder Rates" visible, comment here.

Thanks to all!  Here it is.

8 comments:

  1. This the one?:
    http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2249317

    ReplyDelete
  2. It seems to be active now...

    http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2249317

    ReplyDelete
  3. It's up! 7 downloads so far (8 I guess counting mine.)

    ReplyDelete
  4. It's here.
    https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2249317

    ReplyDelete
  5. Clayton,

    I followed the links others have posted, and dl'd it.

    For time series analysis, econometricians will usually use different statistical methods. In my day (am I showing my age here) it would have been something like the "Chow test." This is essentially the same thing as using a "dummy variable" with "0" for the base case (no background checks) and "1" for years in which there were background checks.

    I would think that the results would be the same as the approach you've taken, but it might be prudent to make sure, as a kind of crosscheck. You have my email address ("blcjr2...."), so if you wish to pursue this, let me know. I have the software to do this in a matter of minutes, if you have the data in a convenient format, like an Excel file.

    Beyond that, I think a potential criticism might be that the sample sizes are too small to draw meaningful inferences. It is the old "absence of evidence is not evidence of absence" conundrum. Just because there is no statistical evidence that background checks had an effect, we cannot thereby conclude that they didn't have an effect. At best, we can only say that there is no evidence that they had an effect. That is, more or less, what you finally conclude ("As a method of reducing murder rates, the evidence in support of it does not exist."), but I would expect that to be the way critics attempt to counteract your analysis.

    Basil

    ReplyDelete
  6. Basil: I am out of town at the moment. I'll forward the data to you when I get home.

    ReplyDelete
  7. Mike Huckabee mentioned your research this AM (4/15) on his radio show! I heard it on the Boise AM radio AM 670.

    ReplyDelete
  8. Excellent! About the only chance that anyone listening to a Boise radio station will hear my name.

    ReplyDelete