# Common sense gun legislation?

**URL:** <https://boards.straightdope.com/t/common-sense-gun-legislation/733300>\
**Category:** Great Debates\
**Created:** [October 2, 2015, 8:48pm UTC](https://boards.straightdope.com/t/common-sense-gun-legislation/733300 "2015-10-02T20:48:20Z")\
**Posts on this page:** 1\
**Showing post:** 591

<div class="post-metadata">

**Author:** ![Bone](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/bone/32/407_2.png) [@Bone](https://boards.straightdope.com/u/Bone)\
**Post date:** [November 26, 2015, 7:18pm UTC](https://boards.straightdope.com/t/common-sense-gun-legislation/733300/591 "2015-11-26T19:18:26Z")

</div>

> [@Hentor\_the\_Barbarian](#):
>
> 1. Which studies have dissimilar control groups and how do they differ?

It was quoted in the post above (second quote box).

> [@](#):
>
> 1. You also seem confused about what having other covariates in the model means. Having other factors in the model that are associated with the outcome means that the study is controlling for important contributing variables. It’s exactly what you and others are crying about! If they accounted for the effect of guns in the home, then there would be no significant association, but they do not. I can explain further if you don’t understand. You may laugh about the science, but it appears that you’re laughing out of either ignorance or desperation.

There is no confusion, but thanks for your fake concern. If you think having double or triple or more risky behaviors among the test group than of the control group is a good basis to compare, that’s great but it’s pretty clearly a crap study.

> [@](#):
>
> 1. You are free to imagine that the guns are brought into the home from another source, since the studies so far do not have a direct measure of that. But studies have included measures of potential mechanisms for this imaginary effect – history of engagement in criminal behavior, history of illicit drug use, socioeconomic status, history of violence in the household… The effect is replicated across samples with various controls for potential mechanisms. In addition, approximately 75% of homicides in these studies are committed by someone known to the victim, and in some studies the effect is not present for people who live alone.

Since I’ve already shown you selectively quote items to present your position more favorably, forgive me if I am skeptical. Of course it’s easy to replicate results when the same weaknesses and flawed methodology is employed. Being consistently wrong is no virtue.

Like I said, it’s a fatal flaw in any study that doesn’t distinguish between the gun that is in the home and one that is brought from outside the home. If you don’t understand that, then I can explain further but I think you might be able to understand it.

> [@](#):
>
> First, the NRA is an advocacy group – of course they decry science that goes against their position as “advocacy.” The suggestion that all the science is not science is a conspiracy theory. Get your tin-foil ready!

A few points:[ol]  
[li]First, there was no suggestion that all the science is not science. [/li][li]Second, this section is completely unresponsive to the part that you quoted. Were you selecting text haphazardly or did you forget to make your point?[/li][li]Third, it’s a given that the NRA has not prevented any actual research, and that the CDC is not prevented from doing research. They are prevented from doing advocacy.[/li][li]Fourth, there is plenty of dollars available for research if it is desired.[/li][li]Fifth, your assertion that, _“you guys are preventng the funding needed to carry out the more specific research”_ is false.[/li][/ol]

> [@](#):
>
> Try to understand this, please. I think you might be able to. Replication is a key to science; something that can be measured reliably should be replicable. So far estimates of DGU based on self-report are not reliable (e.g., they generate estimates between 50,000 to 2.5 million!). Specific examination of self-report reveals problems of telescoping and magnification, problems of implausible reporting (e.g., one person reporting 50 incidents), and evidence that the majority of reported DGUs in such studies are illegal. Again, so you might grasp that, there is manifest evidence of unreliability in the measurement and evidence for the mechanisms of that unreliability.

Again, the problems here are multi-fold.

First, [there have been 13 surveys](http://www.guncite.com/kleckandgertztable1.html)(excluding Kleck) that made an attempt to measure DGU. The lower range you mention of 50K is from the NCVS that did not even ask about DGU. To include that as part of the sample set is misleading. Was that your intent? Of the 13 surveys, 11 attempted to quantify the number of DGU. The range was approximately 775K to 3.6M. Each survey had different methodology so you would expect quantification to differ. [There is more discussion](http://www.guncite.com/gcdgklec.html) at the link if you follow the secondary link - I think you should be able to do that:

> [@](#):
>
> The NCVS was not designed to estimate how often people resist crime using a gun. It was designed primarily to estimate national victimization levels; it incidentally happens to include a few self-protection questions which include response categories covering resistance with a gun. Its survey instrument has been carefully refined and evaluated over the years to do as good a job as possible in getting people to report illegal things which other people have done to them. This is the exact opposite of the task which faces anyone trying to get good DGU estimates–to get people to admit controversial and possibly illegal things which the Rs themselves have done. Therefore, it is neither surprising, nor a reflection on the survey’s designers, to note that the NCVS is singularly ill-suited for estimating the prevalence or incidence of DGU. It is not credible to regard this survey as an acceptable basis for establishing, in even the roughest way, how often Americans use guns for self-protection.

Second, specific examination and evidence that the reported DGU was illegal is only true if you rely on Joyce and anonymous evaluation. Joyce as a reliable source is about as absurd as me expecting you to believe the NRA. At some point gun control advocates and yourself will come to the realization that Joyce, Bloomberg, Kellermann, Hemenway, and their ilk are simply tainted.

Third, you’ve neglected to indicate any measure of DGU that would be acceptable. Can you conceive of any? If an unarmed person starts trying to kick in my door, and through the window they see me display a firearm so they run off, no shots fired, no police report - do you consider that a DGU? If yes, how would that be captured by any study you’d accept? If no, why not?

> [@](#):
>
> Besides which, you’re doing a fine job in your “positive gun news” thread of showing that **the number of DGUs in a year would be somewhere around 110**. If we generously allow for your method catching only 10% of the actual incidents, perhaps there are upwards of 1,100 DGUs per year! Good job, buddy! Thanks for your hard work!

I think a great thing that has come out of that is highlighting your counting ability! First, you estimated slightly less than 1 per week:

> [@Positive Gun News of the Day](https://boards.straightdope.com/t/positive-gun-news-of-the-day/735490/157):
>
> I think this is a great thing you’re doing, bone. It’s not scientific, but at least it provides something to get some kind of read on defensive gun uses. And so far, reaching back to August, you’ve got like 8 incidents or so. **Slightly less than one per week.** That’s great!

Realizing your mistake, after it was pointed out of course, you revised your estimate to about 1,100 DGU per year:

> [@Positive Gun News of the Day](https://boards.straightdope.com/t/positive-gun-news-of-the-day/735490/175):
>
> No, I was just guessing from recollection and from a lack of desire to go back to sift out all the stuff on New Jersey pardons and McAuliffe is terrible and stuff. But it looks like you’re right and I misrepresented the number of incidents you’ve linked to. My apologies.
> 
> So, you’re at about 3 incidents per week (even allowing for the dog shooting and the escalate the argument, shoot and drive away guy and the martial artist who didn’t have a gun). Great! **Maybe about 1,100 DGUs per year**.

(my bold in each of the three sections above)  
And now, you’ve revised yet again, this time moving downward to 110 per year. First I thought it was a typo, but you eliminated that possibility with your 10% extrapolation. So let’s see, about 50, then, about 1100, then, about 110. What was that you were saying about replication?

This is \*almost \*like Kellermann revising his 1986 study stating that a gun in the home is 43 times more likely to kill a family member, friend, or acquaintance than it was used to kill someone in self defense, then 7 years later revising that number to the 2.7 times you are so familiar with - replication! \*Almost \*except Kellermann’s errors were paid for by the CDC - yours are free! Well, they used to be funded by the CDC. Pity it took them so long to wise up.

---

_[View the full topic](https://boards.straightdope.com/t/common-sense-gun-legislation/733300)._
