The Volokh Conspiracy

I have been reading the exchange at the Federalist Society website on the Heller case.

I found the post by Carl Bogus at best uninformed and (unintentionally) misleading. Bogus wrote:

A careful study that compared the nine year period before the ban was enacted with the nine years following enactment, and then compared what happened in D.C. with the immediately surrounding areas in Maryland and Virginia, found that the handgun ban reduced gun-related homicides by 25% and gun-related suicides by 23 percent. Colin Loftin, Ph.D., et al., “Effects of Restrictive Licensing of Handguns of Homicide and Suicide in the District of Columbia,” 325 New Eng. J. Med. 1615 (Dec. 5, 1991). The law did not turn Washington into the Garden of Eden, and crime rates fluctuated, particularly during the last few years of the study when the use of “crack” cocaine was increasing and homicides increased dramatically. Nevertheless, the effect of the law was both immediate and sustained, and things would have been worse without it.

From what I've seen, the Loftin study that Bogus points to should not be taken seriously. A simple Google search would have revealed why. According to Dean Payne’s re-analysis, if you use Loftin’s homicide and suicide data, adjust for population changes (as you must), and use per capita rates (as you must), the DC ban is associated with more deaths after the ban, not fewer. While Payne does not argue that the opposite effect is present, the problems that he points to in the Loftin study should render it useless for answering the question that Bogus wants to answer.

Here is part of the devastating 1994 analysis of the Loftin paper by Dean Payne:

Loftin suggests that the District's 1976 restrictive handgun licensing, effectively a ban on new handguns, prevented an average of 47 deaths per year. Inexplicably, the report fails to mention the rapid shrinkage of the District's population, or the rising population of the surrounding community in Maryland and Virginia. When homicides and suicides rates are expressed as per-capita rates, any apparent post-1976 benefit enjoyed by the District vanishes.

------

The core data of the report shows that the average monthly number of gun-related homicides and suicides dropped significantly in DC after it imposed its handgun ban, whereas non-gun deaths in DC and gun and non-gun deaths in the surrounding MD/VA communities did not drop.

Let me restate that data, but combining gun and non-gun deaths:

Mean numbers of homicides and suicides Loftin, et al. data

.	before ban	after ban	change
Homicide
District of Columbia	20.3	16.7	-18%
Maryland and Virginia	8.8	9.1	+3%
Suicide
District of Columbia	7	6	-14%
Maryland and Virginia	19.1	20	+5%

Note that these are deaths per month, not per-capita rates. The study assured us that there were no significant changes within either group, but did not mention actual population sizes or any growth or shrinkage.

I averaged the populations listed in annual FBI Uniform Crime Reports (UCR) and Census Bureau reports, and found substantial changes in the study areas:

Mean population before and after DC ban

.	before ban	after ban	change
District of Columbia	740,800	639,200	-14%
Maryland and Virginia	2,197,400	2,596,400	18%

I also added up the homicides reported in the UCR. My pre-ban numbers matched Loftin's figures, but the post-ban numbers show a large discrepancy. I find about 100 fewer homicides within DC and about 80 more in MD/VA than are evident in Loftin's numbers. Here are both sets, but expressed as per-capita rates:

Mean annual homicide and suicide rates per 100k residents

.	before	after	change
My homicide count
District of Columbia	32.9	29.9	-9%
Maryland and Virginia	4.8	4.5	-6%
Loftin's homicide rates
District of Columbia	32.8	31.3	-5%
Maryland and Virginia	4.8	4.2	-12%
Loftin's suicide rates
District of Columbia	11.3	11.3	-1%
Maryland and Virginia	10.4	9.3	-11%

Loftin suggests that DC's handgun ban saved 47 lives per year — 3.3 gun-related homicides and 0.6 gun-related suicides per month. This view collapses when the per-capita rates are examined. Some lives were saved by the overall death rate decline visible in both groups, but the body count dropped mostly because many people moved out of the District of Columbia. Body counts in neighboring areas didn't drop simply because the declining death rates were outpaced by a rapidly growing population.

According to my count [but not Loftin’s], the District experienced a 3% better post-ban homicide rate reduction than did the neighboring communities. This is the only portion of the reduced homicide rate that could be attributed to DC's more restrictive handgun control, and amounts to about 6 lives per year. This is too small to be statistically significant.

According to Loftin's numbers, adjusted to a per-capita basis, the District's post-ban benefit vanishes altogether. Its proportionate rate reductions are smaller than those achieved by its neighbors.

It may still be true that the fractions of homicides and suicides related to guns were reduced. This must not be mistaken for a reduction in the actual homicide and suicide rates. Concerning suicide in particular, Loftin's suggestion that this example supports the Zimring-Cook weapons-choice theory over the substitution observed by Sloan-Rivara is directly contrary to the data.

------

Loftin's report dismisses a number of confounding factors, but fails to present adequate justification for doing so. Despite claims to the contrary, the presented measure of lives saved by the District's restrictive handgun policy is structured such that it is inherently contaminated by:

- lives saved by a region-wide drop in homicide and suicide rates from other causes, affecting both study areas;

- lives saved by the population exodus from the District;

- killings in which non-firearms means were substituted for firearms.

My analysis suggests that essentially all of the benefit perceived by Loftin is the result of this or similar contamination.

Finally, the study period ends in 1987, just as Washington DC began suffering a continuing homicide wave that earned it the dishonor of being the Murder Capital of the United States. It is doubtful that many opponents of restrictive handgun controls will be swayed when a city experiencing a doubling of its already horrendous homicide rate is simultaneously heralded as a successful example of such controls.

That the New England Journal of Medicine would publish a time-series article that did not account for population changes over roughly a two-decade period is embarrassing, but then peer review seems to suffer when gun control articles are involved.

I must confess that, unfortunately, this isn’t the first time that Carl Bogus has had trouble with inconvenient evidence. I remember during the dispute over Arming America that Bogus was writing a review and sought my permission to cite one of my unpublished drafts. Before I called him, I confirmed that his own university library’s special collection had a copy of the published Providence Probate records that Michael Bellesiles had used – and grossly misrepresented in Arming America. I called Bogus, gave him the name and number of the reference librarian I spoke with, and tried to get Bogus to spend an hour in his own university’s library confirming that there were major problems with Bellesiles’s account before Bogus finalized his review. Bogus refused even to look at the contrary evidence I urged him to examine, a decision that in part led him to seriously misjudge the work he was reviewing.