While the Lancet numbers are shocking, the study's methodology is not. The scientific community is in agreement over the statistical methods used to collect the data and the validity of the conclusions drawn by the researchers conducting the study. When the prequel to this study appeared two years ago by the same authors (at that time, 100,000 excess deaths were reported), the Chronicle of Higher Education published a long article explaining the support within the scientific community for the methods used. President Bush, however, says he does "not consider it a credible report" and the media refer to the study as "controversial." And even as the Associated Press reported mixed reviews, all the scientists quoted in its piece on the "controversy" were solidly behind the methods used. Indeed, the Washington Post points out that this and the earlier study are the "only ones to estimate mortality in Iraq using scientific methods." ...
There has been a wealth of material on the web attacking the Lancet study. Most of it is devoid of science, and ranges from outrage at the numbers (it's impossible to believe it could be so high), to accusations of bias based on the authors' views of U.S. foreign policy. Interested parties such as the Iraqi government responded quickly by calling the numbers "inflated" and "far from the truth", rather than putting forward any real reasons why these numbers are unlikely to have occurred. The Washington Post reported that the Defense Department's response was that coalition forces "takes enormous precautions," and suggested that the deaths are the "result of insurgent activity". ...
The Lancet study does an excellent job in counting the dead, but its purpose does not lie in pointing fingers. While the study reports that 31 percent of excess deaths were caused by coalition forces, it is possible that those reporting the crimes might be biased by anti-coalition sentiment. Those families may be more likely to believe and report that a violent death was attributable to coalition forces. Of course, bias could go the other direction as well -- we simply do not know. We also cannot assess who died -- civilians or those involved with the armed conflict. Again, it would be easy to see how bias would affect reports by family members.
The methods used by this study are the only scientific methods we have for discovering death rates in war torn countries without the infrastructure to report all deaths through central means. Instead of dismissing over half a million dead people as a political ploy as did Anthony Cordesman of the Center for Strategic & International Studies in Washington, we ought to embrace science as opening our eyes to a tragedy whose death scale has been vastly underestimated until now.
Read the whole thing. There's also a companion piece on the widespread misreporting of the study's results, with the total frequently being described as civilian deaths, even though the study counted all deaths, not just civilian ones.
Interesting that they use the populist, rather than literally correct, definition of a CI:
"The error coming from the use of statistics is found in the confidence interval. In the case of the Iraqi deaths study, the confidence interval for the number of excess deaths is 392,979 to 942,636 people. What this means is that, if the survey were conducted again, we could be 95 percent confident that the excess deaths would fall in this range again."
Great, now if only she could explain the scientific basis for the 2004's study doing the following:
1. Using "cluster clumping". Give me ONE example of another study using this methodology. ONE.
2. What's the scientific basis for pairing up all but five of the governorates in Iraq?
3. What's the scientific basis for the pairings at all? Where's the evidence of the pairs being similar? There is none!
I fear for science if this sort of thing was overlooked by the scientists supposedly endorsing the 2004 study's methodology.
The number of clusters used, even in the 2006 study, will always overrepresent urban areas as they are much more likely to be chosen. You know this, Lambert, but you don't give a damn. You ignored each of the three points above when I brought them up last time, and you'll ignore them again.
This isn't science, this is political propaganda masquerading as science.
"This isn't science, this is political propaganda masquerading as science."
Oh? But then stats.org don't see through it:
"While the Lancet numbers are shocking, the study's methodology is not."
They must be in on the conspiracy!
If I didn't know anything about statistics, I'd only note that opposition does not come from epidemiologists or statisticians, but only from those politically disinclined from believing the numbers, and I'd draw my conclusions from that. Either the mass of people best qualified to evaluate the methods in this study engage in a conspiracy to do political propaganda (and that assumes that they are politically homogenous), or it's the denialists, you know, the right and the pro-war left, who engage in political propaganda.
Harald,
Do you think epidemiologists would come out gunning for their colleagues resulting in less confidence in their own field? Much easier to stay silent, which is what most of them are doing. Find me any number of statisticians who have actually taken the time to read through the entire Lancet study, instead of being quote-shopped by journalists who provided them a brief and misleading overview of the methodology.
But if you really think this stuff is bullet-proof, you should be asking yourself why Lambert and the Lancet-apologists can't answer any of the questions I pose, or refute my challenges.
The fact that demographics weren't even collected by the JHU study seems to give more than enough room to question its validity.
The methodology isn't "shocking" but it isn't good either.
And let me know when you get around to finding those 500,000 "missing" death certificates. I bet they're hiding together with the "missing" WMDs.
Yes, Seixon, they are with the WMDs. In nonexistoville.
And where are the birth certificates? Does Ali al-Shameri have them?
In case anyone wasn't around last year Seixon's questions were answered at length. He just refused to accept the answers. [See here.](http://timlambert.org/index.php?s=seixon&submit=Search)
Seixon, right now I could pose a lot of "challenges" about anything under the sky on my blog. If no expert turned up to refute them, that would hardly be evidence against it. I can't just turn up and demand answers in my place, on my terms.
Even though Tim Lambert has me on his blogroll ;-)
As to your challenges. The one about "missing" death certs I've already explained to you several times. When a bureucracy attempts to collect comprehensive records, it often gives unreliable data in the best of times (which is why several catholics, inluding the bishop in Oslo and my wife, were improperly recorded as state church members for over twenty years. Another scandal for another time.)
To believe that the bureucracy of today's Iraq will be capable of gathering even remotely reliable mortality data is just criminally stupid. Death certificates might not be foremost on a mayor's mind when various violent factions are trying to behead him in the public square?
That particular "challenge" of yours have been answered dozens of times, perhaps first by Daniel Davies of crooked timber.
You pretend to participate in a debate, but you're only trying to make noise as far as I can see. Since you only make this claim again and again, without trying to answer any criticism, I won't care about the rest of your so-called "challenges". No doubt you would continue to trump those, too, no matter how they were met.
If someone reads only your comment and skims the rest, they might think you have a valid point. Seems to me that's all you're gunning for.
"Do you think epidemiologists would come out gunning for their colleagues resulting in less confidence in their own field?"
So your critique is against the field of epidemiology? That is another matter entirely. Because criticism of claims made inside a field is mostly reserved to those in it, it's important that a field as a whole can be criticised. This has happened in the past, with phrenology, marxism (regarded as a science by its adherents) and freudian psychoanalysis to name a few, but not always with merit. Today, it's fashionable to criticise evolutionary psychology and climate science... with varying merit, as I see it.
If this is your mission, good luck to you. But then, I suggest that it is insufficient to attack one study, or studies by one particular author. You'd have to show that the methods employed has been shown to be useless or worse in past experiments. And for all I know, this may be true...
Oh, one thing. If you think it's just this study, or this author's studies that are flawed, then yes, I expect epidemiologists to come out gunning against their colleagues - the reason being that they want to preserve the confidence in their own field. After all, covering up for a flawed study is a very risky and short-term solution. Once things have calmed down, perhaps it may be possible to get more precise numbers, and that would prove very embarrasing to all epidemiologists if the Lancet studies were wildly off.
Sexion: "Do you think epidemiologists would come out gunning for their colleagues resulting in less confidence in their own field?"
Oh God, last time it was the Intewrnational Left Wing journalist conspiracy now it's the International Left Wing Statisticians Conspiracy.
Tell me Seixon, who was it who exposed the Korean clopning scandal? Obviously it wasn't geneticists because it would have "result[ed] in less confidence in their own field"/
Obviously so-called experts in all fields lie constantly to cover for each other.
Onlt those who are totally ignorant about a subject are reliable sources of information on that subject.
Which makes sexion virtually omniscient given the truly remarkable range of topics about which he knows bugger all.
"So your critique is against the field of epidemiology?"
No, Seixon's critique is against all those who dare to question the transcendent revealed Truth that the United States is infallible and ominibenevolopent and if it killed a few hundred thousand arabs it was entitled justified in doing so.
But it didn't.
"The fact that demographics weren't even collected by the JHU study seems to give more than enough room to question its validity."
Except that the "fact" is completely false.
Seixon repeating it gives more than enough room to question his validity.
Someone refresh my memory, was it Seixon or one of the other pro-dead-Iraqi Neanderthals who was loudly proclaiming 6-12 months back that anyone suggesting that there was a civil war in Iraq was a fool and a liar?
"Do you think epidemiologists would come out gunning for their colleagues resulting in less confidence in their own field?"
Yes, the one thing you never find in science is scientists attacking the findings of their competitors for grant money.
"Oh God, last time it was the Intewrnational Left Wing journalist conspiracy now it's the International Left Wing Statisticians Conspiracy."
And here we had been thinking it was the all-powerful and fabulously wealthy climatologist cartel manipulating public opinion to maintain their place at the top of the social pecking order.