Deltoid

EdgarSuter wrote:

whether or not Mr. Lambert disagrees with a single quote of my assessment of the harmful nostrum of gun control, he has yet to explain the habitual fabricated citations of Kellermann (noted in my letter to Emerg Med News)

All right, let’s have a look at the first one:

citation of sources for support when the sources were actually non-supportive; [1(at citations 2 and 15-17), [1] Kellermann AL, Rivara FP, Rushforth NB et al. “Gun ownership as a risk factor for homicide in the home.” N Engl J Med. 1993; 329(15): 1084-91.

Now let’s look at what Kellermann said:

“Homicide rates declined in the United States during the early 1980s but rebounded thereafter.[2]”

The statement is certainly true and the source would be supportive if it has a table giving homicide rates in the 80s.

“Previous studies of risk factors for homicide have employed correlational analysis[15] or retrospective cohort[16] or time-series[17] designs to link rates of homicide to specific risk factors.”

Reference 15 is Cook’s study on robbery which found a link between gun ownership and robbery homicide. Reference 16 is Sloan et al’s Vancouver-Seattle comparison which found more homicides in Seattle. Reference 17 is Loftin et al’s study on the Washington DC gun law which found that the gun homicide rate was significantly less after the ban.

All three studies do say what Kellermann says they do.

Your claims that Kellermann has fabricated citations seem to be unfounded.

Edgar Suter wrote:

From an early DRAFT of Gary Kleck’s TARGETING GUNS : FIREARMS AND THEIR CONTROL scheduled to be published this month:

The Medical/Public Health Literature on Guns and Violence

False Citation of Prior Research

In a 1992 article [Kellermann AL, Rivara FP, Somes G, et al. Suicide in the home in relationship to Gun Ownership. N Engl J Med. 1992; 327: 467-72.], he and his coauthors claimed that “limiting access to firearms could prevent many suicides” (p. 467), citing in support a study (Rich et al. 1990) that had drawn precisely the opposite conclusion. - Rich and his colleagues had summarized the findings of their two studies as-indicating that “gun control legislation may have led to decreased use of guns by suicidal men, but the difference was apparently offset by an increase in suicide by leaping. In the case of men using guns for suicide, these data support a hypothesis of substitution of suicide method” (p. 342).

Hooray! Kleck scores a point! Yes, Kellerman erroneously included this article in their list of supportive studies when it should have been in their list of non-supportive studies. Kleck’s score: 1 out of 11.

In that same article, Kellermann and his colleagues cited an impressive list of six studies (their cites 1015, p. 467) that they claimed had “studied variations in the rates of gun ownership and suicide” across different areas or over time. Of these six, four did not measure gun ownership at all, and thus could not have studied variations in gun ownership (their cites 10, 12, 14, 15),

This is just silly. Cite 15, for example, is Loftin’s study on the DC gun ban. Does Kleck really believe that it didn’t stop the most law-abiding DC residents from acquiring guns?

while one other studied “variation” across just two cities, using measures of gun ownership that turned out to be invalid (their cite 13).

Their cite 13 is the same article as Kleck’s cite “Sloan et al. 1990″ in the next paragraph which Klecks says “actually measured the association between gun ownership and suicide rates”. Is it invalid or isn’t it?

Perhaps it was just coincidence that these falsely cited studies generally drew conclusions supportive of gun control, while the many studies that were relevant (having actually measured the association between gun ownership and suicide rates) but that were not cited, overwhelmingly indicated no significant association between gun levels and total suicide rates (Lester 1987; 1988a; 1988c; 1989b; Clarke and Jones 1989; Lester 1990; Sloan et al. 1990; PB:255256, 268; Killias 1993b; two dissenting studies were Lester 1989b; Moyer and Carrington 1992).

1. No, it is not coincidence that Kellermann, in an article published in 1992, did not cite an article published by Killias in 1993. Possibly it’s because Kellermann does not have a time-travel machine.

2. In any case, Killias in fact found a significant association between gun levels and total suicide rates — exactly the opposite of what Kleck claimed. Yes, that’s right, Kleck has done exactly the thing he has accused Kellermann of.

3. Most of the remaining studies that “overwhelmingly indicated no significant association” were by Lester or Clarke. Lester and Clarke’s summary of what these studies found is a bit different from Kleck’s: “To summmarize,two studies of firearms suggest that increased availability of guns creates additional suicides, two do not, and the third suggests that some but not complete displacement occurs.” Once again we see Kleck counting as “no association” studies that the authors do not.

Charles Scripter wrote:

Here we fit the NSW “before” region to a slope + constant background, while the “after” region is fit only to a slope (chance resulted in this slope passing through, or very close to zero, eliminating the need for a constant, 4th parameter). The origin is located at year 1900.

Data for years 1919 and 1920 were rejected as “anomalous” and the “before” region was extended back to 1907 to offset this loss of data.

It is amazing what you can show if you pick the right subset of the data. In particular, if you want to “find” a decreasing trend, just follow Charles’ example and pick your start year (1907) at a local maximum, and your stop year at a local minimum (1918). Works every time.

Charles’ model:

Rate = (A*Year+B), if Year <=20
        = (C*Year), if Year >20
where A  =  -0.124825 
          B  = 4.00198
          C =  0.0516219  

This additional parameter, and use of slopes rather than constants, results in a fit which is much more pleasing to the eye

The general practice in statistics is to avoid subjective measures like “more pleasing to the eye”. The objective measure favoured is the chi-square test. The chi-square statistic is

sum(((o[i]-e[i])/sd)^2), where o[i] is the ith observation, e[i] is the ith value predicted by the model and sd is the standard deviation.

Since we just want to compare two models, we can multiply through by sd^2 and just work out sum((o[i]-e[i])^2) for each model. The model for which this value is lower has an objectively better fit.

The results (using years 1907-1937):
Charles’s model: 4.96
My step model: 4.43

Charles model has a worse fit, in spite of the fact that his model has more parameters and in spite of the fact that the start year was chosen to favour his model.

This analysis, with it’s positive slope (parameter C) in the post-law region, apparently contradicts the claimed effect of “decreasing homicide rates” correlated with (or “caused” by) 1921 law.

Since you forced the fitted line for the post-law region to go through 0 in 1900, it is impossible for the slope to be anything but positive. If, on the other hand, you allow the line to have an arbitrary intercept, you will discover that the slope is not significantly different from 0.

It is disingenous for Kleck to take a quotation of Kellerman’s out of context to make it appear that Kellermann was asserting that only 2% of of homicides were lawful defensive homicides.

Dan Day wrote:

Well, your own summary isn’t entirely accurate either. Here’s the passage in question:

Less than 2 percent of homicides nationally are considered legally justifiable. [11,13] Although justifiable homicides do not include homicides committed in self-defense, the combined total in our study was still less than one fourth the number of criminal homicides involving a gun kept in the home.

I’ve reread that a number of times and still can’t figure out exactly what Kellermann is trying to say. The best I can make out is that Kellermann is claiming that self-defense homicides are not legally justifiable (?)

You missed the bit where he defined the meaning of those terms: “Self-protection homicides were considered “justifiable” if they involved the killing of a felon during the commision of a crime; they were considered “self-defense” if that was the determination of the investigating police department anf the King County prosecutor’s office.[11]” Reference 11 is the FBI definition of “justifiable homicide”.

Given how Kellermann contrasts “legally justifiable” homicides with “self-defense” homicides, and the passage as written, the point that Kellermann underplayed the number of “lawful defensive” homicides seems a valid one, since it appears he tried to imply that the defensive homicides which fall outside the 2% “legally justifiable” category weren’t in fact lawful.

No, he was pointing out that were lawful homicides that fall outside the 2% legally justifiable.

Dan Day wrote:

I’ve reread that a number of times and still can’t figure out exactly what Kellermann is trying to say. The best I can make out is that Kellermann is claiming that self-defense homicides are not legally justifiable (?)

You missed the bit where he defined the meaning of those terms: “Self-protection homicides were considered “justifiable” if they involved the killing of a felon during the commision of a crime; they were considered “self-defense” if that was the determination of the investigating police department anf the King County prosecutor’s office.[11]” Reference 11 is the FBI definition of “justifiable homicide”.

No, I saw that (upper left on page 1558 of the NEJM publication). I didn’t see as how that clarified Kellermann’s choice of wording on page 1559. And it still leaves open the following questions:

(1) Why the distinction between “self-protection homicides” which are “considered ‘justifiable’”, versus “self-defense”? Ask five different people and you’re likely to get five different opinions on which homicides fall into which category.

Because the FBI and the police make the distinction. The only national data available is for “justifiable homicides” and you can’t refer to that without making the distinction.

(2) Why are only “self-defense” homicides which the prosecutor’s office determined to be self-defense counted as self-defense? Why not the court’s decision?

Because criminal courts are biased towards making sure that people are not punished for crimes they do not commit. So, someone who was probably guilty of criminal homicide, but not guilty beyond reasonable doubt could be found not guilty with a defence of self-defence. That’s fine, but if we are trying to get the best possible estimate of the number of self-defence homicides we should use the standard of civil courts — “more probable” rather than “beyond reasonable doubt”. The decision of the prosecuter’s office seems are reasonable way to estimate whether someone is more likely to be guilty or not.

(3) Why are “all homicides resulting in criminal charges” considered “criminal homicides”, when surely many of them were later found to be justifiable by the courts? (Even many clear-cut cases of defense are referred to the courts by prosecutors because it’s the court’s job to sort out such things, not the prosecutor’s job).

(4) Getting back to the core of the original issue, why did Kellermann choose to word his passage on page 1559 as “Less than 2 percent of homicides nationally are considered legally justifiable”? Most readers, it seems to me, would take this to mean that 98+% of homicides are not considered “legally justifiable” — that is, they’re illegal, or they’re unjustifiable, or both.

I’m sorry, but I see no other way to refer to justifiable homicides, as defined by the FBI, other than to use the term used by the FBI. Not only does Kellermann give the FBI definition (on page 1558), on each of the three occasion when he uses the term, he provides a cite to the FBI definition (cite 11). Furthermore, underneath the passage in question you can see a table classifying the deaths and it is quite clear that the 2 justifiable homicides in the study are a subset of the 9 self-protection homicides.

If, after all this, a reader still manages to misunderstand, I don’t think it is Kellermann’s fault.

And, in any case, this is still no excuse for Kleck’s misrepresentation — Kleck, at least, is well aware of what the FBI mean by “justifiable homicides”.

The final sentence in that paragraph (”A majority of these homicide victims were residents of the house or apartment in which the shooting occurred”) throws further confusion into the mix, seeming to imply (by juxtaposition with the preceding) that if you’re a “resident of the house”, you can’t be the result of a self-defense homicide.

I find your reading of that sentence truly bizarre. Why not take it to mean what it says, and not something else?