"Phil Lee" <[EMAIL PROTECTED]> writes: > Lambert's case, as illustrated in his 3 points below, illustrates an > approach he regularly argues which I'll call the "tobacco company defense." > The argument, which has valid elements, is that correlation between events > (smoking and cancer, hot burglary rates and lack of firearms) do not prove > there is a causal relationship.
You turn the truth on its head. I have pointed out before that there is no correlation between hot burglary rates and gun ownership. See Ludwig and Cook's study. > Correlation might indicate a causal mechanism, but you need to establish the > mechanism some other way than by statistics. Uh huh, but there is no correlation. > Wright and Rossi have claimed > that fear of being shot (with their survey of convicts) is a mechanism and > established through their survey of convicts that the fear is believed real > by convicts. But Lambert quibbles on that point because the survey phrasing > does not really demonstrate the mechanism for the convict questioned, rather > what the convict thinks is true about others. For that quibble to be > considered seriously, you'd have to believe that each convict thought others > in similar circumstances were more fearful than he was. His quibble is a > classic case of using speculation to meet evidence (see Kleck's paper at: > http://www.saf.org/journal/9_evidence.html ) since Lambert presents nothing > other than his speculation. Again you turn the truth on its head. The evidence tells us what they think others believe. It is speculation to argue that they believe the same thing themselves. You can speculate if you want but you should accurately describe what Wright and Rossi's survey found and not make false claims about their findings. They DID NOT conclude that the higher hot burglary rate in Britain was caused by American burglars fear of being shot. > Papers like that cited by Lambert by Ludwig & Cook and other similar > researchers use indirect measures of firearm ownership called a proxy ("new > well-validated proxy for local gun-ownership prevalence"). There is every > reason to be skeptical of gun-ownership proxies because so many of them have > been shown to produce circular arguments. To make an argument here, you need to show that the proxy they used is somehow circular. Which you haven't done. > However, the correlation claimed > in this specific case, "residential burglary rates tend to increase with > community gun prevalence," doesn't pass the smell test as a cause-effect > relationship. Well, maybe I shouldn't say that. Now, *this* is using speculation to meet evidence. > John Lott cites a > cause-effect that criminals move away from direct confrontation crimes such > as robbery, to crimes like burglary in response to "more guns." But, I > wouldn't guess that Lambert would want to quote Lott for a cause-effect > reason in this case. Yeah, mainly because it isn't true. He only gets that result by switching models in mid comparison. With the dummy variable model he got no decrease in burglary and an increase in property crime. With the trend model he got decreases in both. You have to play mix and match games to get the combination of results you cited. And by now it's pretty clear that his models were cherry-picked to give the results he wanted. > Even if it were correct that burglaries increase with gun prevalence, these > authors say nothing in their summary about "post hoc, ergo propter hoc" > issues (chicken and egg for us non-lawyers). Lee's case, as illustrated here, illustrates an approach he regularly argues which I'll call the "tobacco company defense." The argument, which has valid elements, is that correlation between events (smoking and cancer, burglary rates and firearms) do not prove there is a causal relationship. > I'm not familiar with the exact statistical source Professor Olson > describes, but there is a well known U.S. Justice Report showing by most > measures crime rates (except for murder) in England and Wales exceeds that > of the U.S. That report, such a shock to our more civilized cousins in the > rest of the world, may be found at: > http://www.ojp.usdoj.gov/bjs/abstract/cjusew96.htm So crime in England is much less deadly than in the US. Why do you think that is? (BTW, how come you give Olson a title and not me?) -- Tim _______________________________________________ To post, send message to [EMAIL PROTECTED] To subscribe, unsubscribe, change options, or get password, see http://lists.ucla.edu/cgi-bin/mailman/listinfo/firearmsregprof
