Wednesday, August 5, 2015

Guns: More Harm than Good - Obviously

NCBI

Firearm Ownership and Violent Crime in the U.S.: An Ecologic Study.

Abstract

INTRODUCTION:

Although some view the ownership of firearms as a deterrent to crime, the relationship between population-level firearm ownership rates and violent criminal perpetration is unclear. The purpose of this study is to test the association between state-level firearm ownership and violent crime.

METHODS:

State-level rates of household firearm ownership and annual rates of criminal acts from 2001, 2002, and 2004 were analyzed in 2014. Firearm ownership rates were taken from a national survey and crime data were taken from the Federal Bureau of Investigation Uniform Crime Reports. Rates of criminal behavior were estimated as a function of household gun ownership using negative binomial regression models, controlling for several demographic factors.

RESULTS:

Higher levels of firearm ownership were associated with higher levels of firearm assault and firearm robbery. There was also a significant association between firearm ownership and firearm homicide, as well as overall homicide.

CONCLUSIONS:

The findings do not support the hypothesis that higher population firearm ownership rates reduce firearm-associated criminal perpetration. On the contrary, evidence shows that states with higher levels of firearm ownership have an increased risk for violent crimes perpetrated with a firearm. Public health stakeholders should consider the outcomes associated with private firearm ownership.

2 comments:

  1. I love how their results don’t match up with their purpose.

    The purpose of this study is to test the association between state-level firearm ownership and violent crime.

    My emphasis. But then in the results we see nothing about violent crime rates, and instead see “firearm assault”, “firearm robbery”, and “firearm homicide” (a bunch of gun specific crime stats that you guys love to use). I’d get an “F” if I submitted this paper. However, they did throw in “overall homicide” at the end. I tried to dig into this, but it seems they are only providing the abstract, so I can’t check their work. We know the raw numbers are not in their favor (I’ve been over that countless times). But this study was using statistical modeling with multivariable regression. I have mentioned before that any statistician worth one’s salt can manipulate a model to say whatever they want it to say by picking what “demographic factors” to control for and how to do it. That’s the beauty of the raw numbers I always show. You can’t manipulate them. They are limited in what they can reveal- like you can’t draw causative statements from them (but I’m not trying to). A classic example of “controlling for other factors” as a way of manipulating the outcome is the Harvard paper we discussed recently. They controlled for crack cocaine use (which in itself isn’t a bad idea), but they didn’t control for any other drugs like heroine, meth, powered coke, etc. So as crack became less fashionable into the new millennium their model predicted that murder rates would continue to fall like they did from their peak in the early 90s (which would probably put our murder rate in the negative by now), and then when it didn’t, the study blamed it on guns- even though crime kept dropping while more and more guns were put into circulation. Absurd. And you can see how easy it is for a statistician to manipulate it to come out that way.

    Even their conclusion is a straw man:

    The findings do not support the hypothesis that higher population firearm ownership rates reduce firearm-associated criminal perpetration.

    Who says “firearm-associated” crimes? If they are talking about John Lott, he says “all crime”.

    ReplyDelete
  2. Key concerns of this particular "study" the rate is an inherently misleading static as higher population areas often have dramatically more murders, in absolute numbers than the lower population more rural areas. Another issue is the fact that they untilize the homicide statistic, not murder which would be a more accurate metric when trying to make your case. And as is often the case they don't clarify if they counted statistics in which the firearm is utlilized in the commission of a crime or just in the crimjnals possession at the time of committing the crime, as while both would be considered "gun crime" the reality of what they mea is dramatically different.

    ReplyDelete