Wednesday, 10 September 2003

Lott, liberty, and the pursuit of econometrics

Tim Lambert does a pretty good job demolishing John Lott’s latest evasions; I think the key quote (buried in Lambert’s effort to prove that Lott played games with a table) is here:

Plassmann was kind enough to reply. He conceded that no significant results remain after correcting the coding errors and did not know why Lott had removed the clustering correction [from his Stata .do file]. I also posted my question on the firearmsregprof list (also CC’d to Lott because I am very courteous). No-one there knew of a reason either.

However—accepting that Ayers and Donahue do it right—there’s still the issue of null results. More guns may not mean less crime, but the results clearly show that more guns don’t mean more crime either, and the signs indicate that concluding “more” has less support than concluding “less,” although you’d have to be an idiot to come to either conclusion based on the Ayers and Donahue corrections to Lott’s results (that’s why we call them “not statistically significant”). Then again, “More Guns, No Effect On Crime—Either Way” isn’t a very sexy book title.

More fundamentally, the “null results” return the issue of gun rights back to the realm of philosophy, the area where all rights ought to be debated in the first place. My view is that public policy is, and should be, the subject of empirical debate, while (in general) fundamental rights and liberties should not. An example: even if we proved empirically that 99.9% of coerced confessions were made by people who actually committed crimes, that would not be a valid justification for law enforcement to violate the 4th and 8th amendments to the Constitution.

CalPundit has more. I’ve also clarified that the Ayers and Donahue corrections to Lott’s results are not their results (which I haven’t looked at in any great detail, although I did download their data and stare blankly at the Stata files for a few minutes a few months back when it came out; I do remember them logging everything, which at least proves they learned their stats from economists).

Link via InstaPundit.