So far, beyond the cross dressing, which is just sort of humorous, we knew that John Lott was at best guilty of irresponsibility with numbers that bordered on the fraudulent (e.g. making claims based on 13-instance samples) and at worst, outright fabrication of a survey. Well, if you were still keeping your fingers crossed for vindication, Tim Lambert has located a pretty conclusive attempt by Lott to retro-fabricate a data table in order to disguise some ad-hoc model tweaking. CalPundit has an excellent, clear summary. It’s long past time for people who care about gun rights to cut this albatross from our necks.
A Statistical Albatross
September 12th, 2003 · No Comments