That Iraqi bloodbath.

Who can imagine all the effort and expense that went into getting those Iraqi civilian casualty figures published just before the American elections!

Be that as it may, some commenters to "J'accuse: Iraq the Model responds to the Lancet Lies" suggest that the results of the Lancet study of Iraqi casualties is, . . . umm, flawed:

[T]he study found 547 actual deaths in their surveyed group and extrapolated a mind boggling 655,000 from such a miniscule sample.

Steve Schippert.

Keep in mind, the violence is almost entirely in three provinces. This isn't 600K out of 25M, it's 600K out of maybe 10M.

We would expect to find wounded at about five times that rate. That would mean about 3M wounded, or nearly 1 in 3 Iraqis in those areas-- man, women and child. Does sound reasonable to anyone?

TallDave

There's a sort of historical innumeracy at work here. 650,000 violent deaths is about 150,000 more than the number of soldiers who died (violently and by disease) during the American Civil War, a conflict which involved a population about 50% larger than Iraq's, which lasted a year than the current conflict has been going on, and was fought over continental distances. There is nothing in Iraq that looks like Shiloh, Antietam, Gettysburg, Cold Harbor, etc. As terrye notes, this figure is absurd.

Cheng-Jih Chen

The mortality rate in the EU is 10.10/1000.

The Mortality rate in the US is 8.5/1000.

The mortality rate in Hungary is 13/1000

The world average mortality rate is 8.5/1000 per year.

The Lancet study uses a "baseline" mortality rate of 5.5. Half the mortality rate of Europe.

Soldier's Dad.

"J'accuse: Iraq the Model responds to the Lancet Lies." Politics Central^TM, 10/11/06.

UPDATE (10/19/06):
Steven Moore adds some more pointed comments on this study:

But the Johns Hopkins tally is wildly at odds with any numbers I have seen in that country. Survey results frequently have a margin of error of plus or minus 3% or 5%--not 1200%.

The group--associated with the Johns Hopkins Bloomberg School of Public Health--employed cluster sampling for in-person interviews, which is the methodology that I and most researchers use in developing countries. . . . Neighborhoods are selected at random, and then individuals are selected at random in "clusters" within each neighborhood for door-to-door interviews. . . .

However, the key to the validity of cluster sampling is to use enough cluster points. In their 2006 report, . . . the Johns Hopkins team says it used 47 cluster points for their sample of 1,849 interviews. This is astonishing: I wouldn't survey a junior high school, no less an entire country, using only 47 cluster points.

Neither would anyone else. . . . [T]hat is an extraordinarily small number of cluster points. . . .

Mr. Moore also discusses the problem of Johns Hopkins team's failing to obtain demographic data.

"655,000 War Dead? A bogus study on Iraq casualties." By Steven E. Moore, Wall Street Journal, 10/18/06.