[lbo-talk] Southern vs. Northern violence

Miles Jackson cqmv at pdx.edu
Sun May 6 12:37:16 PDT 2007


Michael McIntyre wrote:
> I did some quick checking of homicide rates to see if violence is
> higher in northern or southern cities. The strange answer, looking
> at raw homicide rates, seems to be that border cities are
> disproportionately bad.
> 2004 Unadjusted Ranking
> 1. New Orleans
> 2. Baltimore
> 3. Detroit
> 4. Washington, D.C.
> 5. St. Louis
>
>
> What happens, though, if you take out the "five highly
> intercorrelated variables (factor loadings in parentheses): the
> poverty rate (.934), male unemployment rate (.888), % black (.839), %
> female-headed families w/own children under 18 (.928), and median
> family income (-.862)". (http://www.cjgsu.net/initiatives/
> HomRates-2005-12-06.htm) The adjusted homicide rates give a very
> surprising ranking. (http://www.cjgsu.net/initiatives/
> HomRates-2005-12-06-Score.pdf)
> 1. San Francisco
> 2. Washington, D.C.
> 3. New Orleans
> 4. Baltimore
> 5. Kansas City

I don't get the point of this multiple regression model. What the guy did was partial out various sociodemographic factors (not just those above, but also divorce rate, population, and residence stability) to create the "adjusted" ratings above. So if the cities were equivalent on all these sociodemographic factors that are in fact integral to urban life in that city, the cities would show the "adjusted" rankings. So what? You're still more likely to be a homicide victim in New Orleans than in San Francisco.

Miles



More information about the lbo-talk mailing list