More Brady Campaign Score correlations

I updated my Brady Campaign Score for state gun laws correlations. Previously I used FBI UCR data from 2005 with Brady Scores from 2007. My present results use only 2007 data and added correlations for the total violent crime rate, murder, and rape. The spreadsheet is here but the interesting part is as follows:

FBI Data Type

Correlation Coefficient

Violent crime rate per 100K


Murder and nonnegligent manslaughter rate per 100K


Forcible rape rate per 100K


Percent murdered with firearm


Percent murdered with knife


Percent murdered with weapon other than firearm


Percent murdered with hands, fists, feet, etc.



The correlation coefficient always takes a value between -1 and 1, with 1 or -1 indicating perfect correlation (all points would lie along a straight line in this case). A positive correlation indicates a positive association between the variables (increasing values in one variable correspond to increasing values in the other variable), while a negative correlation indicates a negative association between the variables (increasing values is one variable correspond to decreasing values in the other variable). A correlation value close to 0 indicates no association between the variables.

For the most part there is no correlation between Brady Scores and the crime data. The exceptions are there does appear to be a moderate association between good Brady Scores and a decrease in rape and slight increase in the chances that if someone is murdered they will be murdered with a knife in Brady approved states.

The rape data point is a mystery to me. Most men have enough of a physical advantage on the average woman that having “easy access” to a gun would not seem to be an important part of forcing a female victim to comply. If “easy access” to guns were to enable any crime I would think it would be murder or even violent crime in general. But that does not seem to be the case.

Also of interest is that the FBI has footnotes explaining that Illinois didn’t supply much data and that for some unexplained reason Florida was not included in Table 20.

Any speculation, other than random coincidence, on why there is a negative correlation between good Brady Scores and rape rates?


8 thoughts on “More Brady Campaign Score correlations

  1. SWAGing here, I suspect that the key is that rape is NOT about sex, but rather about domination. Maybe this is a case where the pop-psych equation of “gun = penis-substitute” holds water. (And Freud really did say that an irrational fear of weapons is a sign of an immature mind; it was not in a book, but in a letter.)

  2. Personally (and I am not a psychologist, and barely a statistician), I would venture to guess that the correlation between rape and Brady Scores is possibly due to the perpetrators knowing that their victims stand a better chance of being unarmed, and thus less capable of defending themselves, than in other states.

  3. Well… Don’t be too hard on yourself.

    My original wording wasn’t all that clear and after your confusion I tweaked the wording a little be so it was less likely to be misunderstood.

  4. I claim that the magnitude of the correlation coefficients are too small to make any conclusions given the size of the data set. Random fluctuations.

  5. Joe, I applaud what you are doing here. Remember that you’re looking at one year of UCR data; the data reporting is voluntary, and that it includes only crimes known to reporting agencies. I doubt the data encompasses all forcible rapes that occurred, but only those that were reported.

  6. Maybe its because these areas also tend to have a higher than average rate of homosexual males? 😀

Comments are closed.