This New York Times investigation into murders committed by Iraq II and Afghanistan veterans has got plenty of right-of-center commentators fuming.

For those that missed it or need a refresher, here is a quick recap from the first story in the NYT series which ran on the 13th:

The New York Times found 121 cases in which veterans of Iraq and Afghanistan committed a killing in this country, or were charged with one, after their return from war.

To compile and analyze its list, The Times conducted a search of local news reports, examined police, court and military records and interviewed the defendants, their lawyers and families, the victims' families and military and law enforcement officials.

This reporting most likely uncovered only the minimum number of such cases, given that not all killings, especially in big cities and on military bases, are reported publicly or in detail.

And where would we be without this most Times-ian of nut graphs:

...these killings provide a kind of echo sounding for the profound depths to which some veterans have fallen, whether at the bottom of a downward spiral or in a sudden burst of violence.

Besides documenting the often horrific murders -- and giving valuable insight into the at times suffocating stress that some veterans live with -- the general claim of the piece seemed to be that the number of murders committed by veterans has gone up since the start of the war:

The Times used the same methods to research homicides involving all active-duty military personnel and new veterans for the six years before and after the present wartime period began with the invasion of Afghanistan in 2001.

This showed an 89 percent increase during the present wartime period, to 349 cases from 184, about three-quarters of which involved Iraq and Afghanistan war veterans. The increase occurred even though there have been fewer troops stationed in the United States in the last six years and the American homicide rate has been, on average, lower.

Unfortunately, there's no evidence from the story that a robust statistical analysis was done with this comparison. Quoted in the NYT piece, Lt. Colonel Les Melnyk, a Pentagon spokesperson,

questioned the validity of comparing prewar and wartime numbers based on news media reports, saying that the current increase might be explained by "an increase in awareness of military service by reporters since 9/11."

For their part, the critics in the blogosphere and various attached groups argue that the Times never compares the murder rate among veterans with the current murder rate among the general population.

Looking through this interactive on NYT's site which documents nearly each individual case, it's apparent that those charged with murder (or manslaughter in a number of cases) are almost all under the age of 50.

According to the F.B.I., in 2006 the number of male offenders in the general population between the ages of 18 and 50 who committed murder was 10,067.

That same year, NYT found 32 similar cases among veterans. 2006 was also the year with the most documented cases of killings by veterans.

The number of males in the general population between 18 and 50 is about 67 million. It's hard to come up with the number males between 18 and 50 who served in Iraq and Afghanistan.

According to the Pentagon, there were 265,501 troops deployed in support of Operation Iraq Freedom and 1.6 million members who were ever deployed in support of OIF as of November.

Let's be very conservative and say that any one time in 2006 there were 600,000 residents in the United States that at some point served in Iraq or Afghanistan.

So, the murder rate for those 18 to 50 in 2006 was 0.015 percent while the murder rate for veterans in 2006 was 0.0055 percent.

My admittedly crude calculation would imply that murder is less prominent among veterans of Iraq and Afghanistan.

(This other back-of-the-envelope analysis arrives at a similar conclusion.)

The Times, however, says that they never made the claim that murders committed by veterans were more prevalent than the average population.

Here's a statement from spokesperson Diane McNulty:

The article did not suggest, contrary to what many of its critics have said, that returning war veterans were more likely than civilians in their age group to commit homicide or manslaughter. Neither the military, nor the Justice Department keeps statistics on the kinds of cases we examined. The military's rates, such as they are, are based on cases it prosecutes, which is very few since 70 percent of service personnel live off bases and many crimes committed are handled by civilian authorities. That is why the article said that the list of homicides it examined - drawn from media reports and then reported out - was not complete. The relevant comparison - as suggested by experts with whom we consulted - was to take a snapshot of before and after the wartime period using this same method, again drawing from reports in the media and supplementing with our own reporting. Again, we said it was not scientific or precise, but at least it was an apples-to-apples comparison.

McNulty further says that the intent of the series is primarily to question "how combat trauma is being addressed in the current population of returning veterans."

For the most part, that seems sensible, but it's still surprising given how contentious the piece's topic would likely be, that the original story never explicitly stated that killings by veterans were below that of the average population.

More importantly, since the statistics were presented so prominently at the beginning of the piece, I wonder how many people were left with the impression of the opposite?

Other researchers have found little evidence that war trauma negatively effects the majority of veterans. In fact, it actually makes them more civic-minded.

Chris Blattman, an assistant professor of political science and economics at Yale, has looked into how child and young adult soldiers in northern Uganda fared after war in that country. He writes on his blog:

Former child and adult recruits are a fifth more likely to vote, are more than twice as likely to be community leaders, and are no more violent than their peers. The reason? Violence, it seems, activates and empowers youth as or more often than it defeats them.

(Full disclosure: I worked at the Times for 2.5 years through 2006.)

UPDATE
The NYT's public editor weighs in:

...the questionable statistics muddy the message. A handful of killings caused by the stresses of war would be too many and cause for action. Sometimes, trying to turn such stories into data -- with implications of statistical proof and that old journalistic convention, the trend -- harms rather than helps.

And the STATS blog has some important criticism for critics like me:

...comparing the homicide rate of veterans with the homicide rate of the general population aged 18-34 and then noting that the latter is higher than the former (ergo, combat is not predictive of increased PTSD, violence or whatever) is a poor way of conceptualizing an answer to the question of whether exposure to combat is predictive of increased rates of violence in veterans.