Underpants Gnomes Statistics & Research.

The Cult Coalition to Stop Gun Rights Violence is all giddy this morning with the following:

CSGV DATAI found the report’s website and being the cheap bastard I am, I decided not to waste my money buying it, specially after I read the “study” method:

Methods. We conducted a negative binomial regression analysis of panel data from the Centers for Disease Control and Prevention’s Web-Based Injury Statistics Query and Reporting Systems database on gun ownership and firearm homicide rates across all 50 states during 1981 to 2010. We determined fixed effects for year, accounted for clustering within states with generalized estimating equations, and controlled for potential state-level confounders.

Wait, what gun ownership database? Again, What gun ownership database across 50 states? How can you make a study using something that does not exist? I know darn well that Florida does not have a Gun Registry of any kind so there goes the 50 states quote. In fact, how many states have a gun registry, much less an accurate gun registry?

I am sure we will be seeing some serious peer review later, but so far things do not look good for the study. Probably they took their statistical cues from the same people who created the formulas to determine the number of hurricanes we will have during any given year or the advance of global warming.

 

7 Replies to “Underpants Gnomes Statistics & Research.”

  1. I predict the course of the study will be boring…

    We have a brand new impressive study with a snappy and provactive title and superficial scary “findings” which gets the anti-gunners light-headed with tingles up their legs as they proclaim it from the mountaintop that all guns should be banned because science says so.

    Then, when the first wave of criticism/fisking comes out they will act indignant and launch the ad hominem attacks.

    …and years later, they will continue to cite it as fact after the study has been thoroughly debunked, but it will have been established in the minds of the low-information voters (whom they will target for skewed polls later).




    0



    0
    1. Wow, that’s pathetic. Maybe the debunking can occur ahead of schedule due to the use of suicides as a surrogate for firearms ownership.

      On the plus side, they mention that it is a peer-reviewed study, but it does not guarantee objectivity. Just look at medical professionals that declare “gun violence” to be an epidemic, just like an infectious disease!

      Not much credibility when they dabble in subjects outside their area of expertise. Alignment with heavily biased “researchers” does not help.

      Another case of “Garbage In – Garbage Out” probably.




      0



      0
  2. I’m waiting to see how they bridge the gap between correlation and causation.

    To my eye, the causation could easily run the other way: People in high murder rate areas can be expected to be more concerned about their safety and thus more likely to own guns.




    0



    0
    1. “People in high murder rate areas can be expected to be more concerned about their safety and thus more likely to own guns.”

      Unfortunately people in places like Chicago and DC do not have easy access to guns legally. That is why you see the higher murder rate.




      0



      0

Feel free to express your opinions. Trolling, overly cussing and Internet Commandos will not be tolerated .