It is an unseemly thing to be debating how many Iraqis have died as a result of the invasion and occupation by US troops. I’m absolutely sure that most opponents of the war feel that way. They would, I’m sure, wish that we would all just sit back and accept the politically motivated study released today that purports to show 600,000 more Iraqis have died since 2003 than would have if we hadn’t invaded:
A team of American and Iraqi public health researchers has estimated that 600,000 civilians have died in violence across Iraq since the 2003 American invasion, the highest estimate ever for the toll of the war here.The figure breaks down to about 15,000 violent deaths a month, a number that is quadruple the one for July given by Iraqi government hospitals and the morgue in Baghdad and published last month in a United Nations report in Iraq. That month was the highest for Iraqi civilian deaths since the American invasion.
But it is an estimate and not a precise count, and researchers acknowledged a margin of error that ranged from 426,369 to 793,663 deaths.
First of all, the Times makes a common mistake by lumping civilians, insurgents, and Iraqi Police and Army units all together and simply referring to them as “civilians.” In fact, the study makes absolutely no effort to differentiate between civilians and insurgents, Police and army. All the researchers asked were the number of dead over the last 3 years.
But why is the study politically motivated?
This is the same crew whose 2004 study showing 100,000 Iraqi dead was thoroughly debunked by a wide variety of experts from both sides of the debate.
Fred Kaplan of Slate on the 2004 study:
“Readers who are accustomed to perusing statistical documents know what the set of numbers in the parentheses means. For the other 99.9 percent of you, I’ll spell it out in plain English—which, disturbingly, the study never does. It means that the authors are 95 percent confident that the war-caused deaths totaled some number between 8,000 and 194,000. (The number cited in plain language—98,000—is roughly at the halfway point in this absurdly vast range.)This isn’t an estimate. It’s a dart board.
Imagine reading a poll reporting that George W. Bush will win somewhere between 4 percent and 96 percent of the votes in this Tuesday’s election. You would say that this is a useless poll and that something must have gone terribly wrong with the sampling. The same is true of the Lancet article: It’s a useless study; something went terribly wrong with the sampling.”
As you can see from the above New York Times excerpt, these purveyors of wildly exaggerated mortality have tried the same technique this time around as well: they have “a margin of error that ranged from 426,369 to 793,663 deaths.”
What’s more, this excerpt from the original NY Times article of October 29, 2004 could have been pasted into their article today:
“Editors of The Lancet, the London-based medical publication, where an article describing the study is scheduled to appear, decided not to wait for the normal publication date next week, but to place the research online Friday, apparently so it could circulate before the election.â€
Funny how these studies seem to show up around election day, eh? Color me suspicious, but if the study had come out 3 weeks after the election, I would be more sanguine about the author’s motives.
The Washington Post tries to put the best face on the study by quoting non-experts who seem satisfied with the results but curiously, all seem to be unanimously against the US occupation. But putting a ball gown on a sow still gives you a pig all dressed up with nowhere to go:
Ronald Waldman, an epidemiologist at Columbia University who worked at the Centers for Disease Control and Prevention for many years, called the survey method “tried and true,” and added that “this is the best estimate of mortality we have.”This viewed was echoed by Sarah Leah Whitson, an official of Human Rights Watch in New York, who said, “We have no reason to question the findings or the accuracy” of the survey.
“I expect that people will be surprised by these figures,” she said. “I think it is very important that, rather than questioning them, people realize there is very, very little reliable data coming out of Iraq.”
Ms. Whitson’s take is interesting. There is “no reason to question the findings” of a study using, despite what Mr. Waldman says, questionable methodology 3 weeks before an election. She actually wishes critics would just sit back and shut up because – and here she inadvertently debunks the study herself - “there is very, very little reliable data coming out of Iraq.”
At least give the Times credit for including some cautionary voices in its article:
Robert Blendon, director of the Harvard Program on Public Opinion and Health and Social Policy, said interviewing urban dwellers chosen at random was “the best of what you can expect in a war zone.â€But he said the number of deaths in the families interviewed — 547 in the post-invasion period versus 82 in a similar period before the invasion — was too few to extrapolate up to more than 600,000 deaths across the country.
Donald Berry, chairman of biostatistics at M. D. Anderson Cancer Center in Houston, was even more troubled by the study, which he said had “a tone of accuracy that’s just inappropriate.â€
In other words, the researchers were able to discover and confirm 547 dead in the post invasion period by interviewing a little more than 1800 families. And from that sample, they extrapolate 600,000 dead.
What’s wrong with that picture?
There are other sources for counting Iraqi dead. The well respected Iraq Body Count, run by academics opposed to the war, lists nearly 49,000 civilian dead since the invasion. Their methodology is sound and their numbers are based on actual reports from morgues, the media, and the military. Their number of confirmed dead is still less than half the number estimated in the 2004 Lancet study.
Someone is wildly off base here. Could it be the group that says that the US military has killed 180,000 Iraqis as a direct result of military actions?
Gunshot wounds caused 56 percent of violent deaths, with car bombs and other explosions causing 14 percent, according to the survey results. Of the violent deaths that occurred after the invasion, 31 percent were caused by coalition forces or airstrikes, the respondents said.
The fact that those three percentages totalled up equal 101% isn’t as ridiculous as 31% of deaths were caused by coalition forces or airstrikes. And here we get to the number one critique of this study and why it so totally useless:
Again, the study makes absolutely no effort to differentiate between innocent civilians and Iraqis trying to kill our troops. Nor does it differentiate between civilian deaths and the deaths in the Iraqi police and armed forces.
In addition, the study includes deaths that the researchers have arbitrarily determined were caused by the invasion but not caused by violence. If they are using the same criteria as the 2004 study, some of these causes of death include:
- Malnourishment due to bad economic conditions as a result of the invasion.
- Illness due to degraded health care infrastructure.
- Deaths due to domestic violence.
- Deaths due to criminal activity unrelated to the insurgency.
- And “... civilian deaths resulting from the breakdown in law and order, and deaths due to inadequate health care or sanitation.â€
Of course, the political problem engendered by this pseudo-scientific hit piece is that the left will use this figure without any caveats and state flatly in their critiques of the war that 600,000 civilians have died as a result of our invasion. And by the time the study is once again debunked by those who know a helluva lot more about statistics and such than I, the lie will have taken hold and the myth will have been set in stone.
And the American people are treated to one more October surprise before casting their vote on November 7.
6:37 am
this study is nothing more than a pack of leftist/partisan/”anti-war” distortions released in OCTOBER before a big election.
7:12 am
Nice job on debunking propaganda masquerading as research.
I was struck by the precision of the confidence limits—426,369 to 793,663. Six digits of precision! If you say that 426,368 died, that figure falls outside the limits, but 426,369 is likely at the 95-percent confidence level. So precisely measured, it must be scientific! The Lancet article is truly an insult to our intelligence.
7:13 am
Nice study. Did they also conclude that 9/11 was a hoax, 3 Jews died in the holocaust, and Democrats would win the November elections?
7:27 am
Even the methodology from the website Iraqi Bodycount is horribly flawed. They don’t examine morgue reports, nor do they have anyone on the ground. They merely scour news articles and print the high and the low in the articles. There is no confirmation of the information other than the articles. It’s useless, just like the Lancet.
8:15 am
Report on 655,000 alleged Iraqi civilian casualties since the beginning of the Iraq war: the latest October surprise
It’s all over the news – Memeorandum has it at the top of their page, so it’s getting a lot of play in the blogosphere as well. Here’s the Washington Post headline: Study Claims Iraq’s ‘Excess’ Death Toll Has Reache…
8:15 am
Report on 655,000 alleged Iraqi civilian casualties since the beginning of the Iraq war: the latest October surprise
It’s all over the news – Memeorandum has it at the top of their page, so it’s getting a lot of play in the blogosphere as well. Here’s the Washington Post headline: Study Claims Iraq’s ‘Excess’ Death Toll Has Reache…
8:15 am
Report on 655,000 alleged Iraqi civilian casualties since the beginning of the Iraq war: the latest October surprise
It’s all over the news – Memeorandum has it at the top of their page, so it’s getting a lot of play in the blogosphere as well. Here’s the Washington Post headline: Study Claims Iraq’s ‘Excess’ Death Toll Has Reache…
8:20 am
The Lancet’s October Surprise:
Rick Moran goes through the Johns Hopkins’ researchers study claiming that more than 600,000 civilians have died in Iraq since the war started in 2003. (Right Wing Nut House)...
8:56 am
I don’t believe that 600,000 Iraqis have died since the invasion at all. Not just how they died or who they were, but that they died at all.
I am sure that this study did conflate all the dead, but keep in mind that Iraq has a population of about 27 million. Where were all the funerals? If my math is right that is about 570 a day, every day. Where are they?
8:57 am
[...] The new Johns Hopkins/Lancet study of deaths in Iraq caused rightie knees to jerk so fast I’ll bet a bunch of ‘em are on crutches today. [...]
9:05 am
Thanks for a detailed analysis. I saw this “piece of leftist junk” in another newspaper this morning. Off course every leftist outlet will have a field day with this cooked up study. These turncoats don’t care how many of our young men are dying to protect all those comfy corner offices where leftists can sit and write these junk studies.
9:12 am
And the study doesn’t take into consideration how many Iraqis Saddam Hussein would have killed had he remained in power. By most Bush Administration estimates, if the rate of killing under his regime had continued, there would be not one Iraqi left alive by now.
The Iraqi just don’t know how lucky they are to have Americans there bringing them peace, security and the blessings of democracy.
9:12 am
The Iraq Death Toll Study
Interesting timing.NEW YORK (AP)—A controversial new study contends nearly 655,000 Iraqis have died because of the war, suggesting a far higher death toll than other estimates. The timing of the survey’s release, just a few weeks before the…
9:16 am
Let’s face it – journalists are suckers for ‘studies’ that confirm preconceived biases. “Super Bowl Sunday domestic violence,” anyone?
9:32 am
Another bogus lancet study
Now the Lancet wants us to believe that 655,000 people have died as a result of the US invasion of Iraq since 2003.
A team of American and Iraqi epidemiologists estimates that 655,000 more people have died in Iraq since coalition forces arrived in Marc…
9:41 am
Here is a free .pdf of the study:
http://www.thelancet.com/webfiles/images/journals/lancet/s0140673606694919.pdf
The numbers reported are absurd. Note: the researchers estimate that 654,965 people died (in total) post invasion. They estimate that 601,027 died as a result of violence. That means that in three and one third years, only 53,938 people died from all other causes combined – in a population of 27 million. That’s 90,000,000 person years, 54,000 deaths, which means that the annual death rate (excluding violence) is 0.0006. Which implies that, on average, people who don’t die of violence are living to be 1,668 years old.
Well done, Lancet. Report your results with confidence.
9:45 am
Sorry, ignore that. There were 654,965 “excess” deaths, not total deaths.
9:47 am
[...] Rick Moran “Ms. Whitson’s take is interesting. There is “no reason to question the findings†of a study using, despite what Mr. Waldman says, questionable methodology 3 weeks before an election. She actually wishes critics would just sit back and shut up because – and here she inadvertently debunks the study herself – “there is very, very little reliable data coming out of Iraq.— [...]
9:49 am
[...] Plenty of people argue these numbers are crazy, absurd, liberal in the worst sense, the source of ghoulish debate. If the method is true, how can the results be argued with now? Ronald Waldman, an epidemiologist at Columbia University who worked at the Centers for Disease Control and Prevention for many years, called the survey method “tried and true,” and added that “this is the best estimate of mortality we have.” [...]
9:59 am
Report: 655,000 Iraqi Civilians Have Died Since Start Of Iraq War
I question the timing. And, apparently, so does the Associated Press. A controversial new study contends nearly 655,000 Iraqis have died because of the war, suggesting a far higher death toll than other estimates. The timing of the survey’s release,...
10:02 am
[...] If you haven’t heard the newest excess death totals yet, find out about it here. Basically, that number represents the additional people who have died because of invasion. And it doesn’t simply count violent deaths. The researchers factored in increased mortality due to poor economic conditions, etc. In the interest of equal time, Right Wing NutHouse has some counterpoints here. [...]
10:07 am
[...] Anyway. Moran does his best to debunk, although it worth’s noting that the two key criticisms of the previous study — that the sample was too limited and the margin of error too wide — are limited in this case. According to the Times, the sample wasn’t taken in areas where violence was “clustered,” it was taken in 47 different neighborhoods across the country. And whereas the low-end figure for the margin of error in the previous study was 8,000 (and the high end 194,000), in this case the low end is … 426,000 and change. That’s about the same number of Americans killed in World War II. [...]
10:16 am
I looked at the study and found it false because 2+2 is clearly 5.
Well done Morgan, report your results with confidence!
10:22 am
From my commentary at Gatewaypundit:
Then you look at something like the actual death rate in Iraq circa 2002 which was estimated at 6.02 deaths per 1,000 from the folks at history central, and then compare them to the estimated death rate for this year which is 5.37 per 1,000 from indexmundi. So, from before the war to today the actual death rate per 1,000 has DROPPED by nearly 9%.
And we are to believe that more have died above the regular amount under Saddam while the death rate for the entire population has fallen? And while the population has also increased by a bit over 2 million people, to boot! So, the deaths attributable to war have actually lowered the overall death rate in the population, increased population, and increased life expectancy from 67.38 years at birth to 69.01 years at birth. Also note that infant mortality has gone down from 57.61 per 1,000 live births to 48.64 per 1,000 live births.
So, even with an increasing population the death rate has fallen in proportion to the entire population… not something you can expect from you basic concept of warfare. If this is war then it needs to be practiced on a global scale because, by all measures of life expectancy, death rates, infant mortality, and, basically, all demographic measurements, the Iraqi people are way more better off today and living longer lives and increasing their population.
Funny kind of war, that.
10:23 am
The Lancet does it again
The once-venerable medical journal is at it again with their pre-American election propaganda. Rick covers it. Truly propaganda masquerading as statistics, dishonest, wrong – and shameful.
10:27 am
[...] Since Election Day is around the corner, the left-wing propagandists at the British medical Journal Lancet (which used to be one of the premier medical journals in the world) have decided to update the thoroughly debunked study which they published around Election Day 2004. That study purported that almost 200,000 Iraqi civilians had been killed in the Iraq War. The updated study claims that 600,000 Iraqi civilians have so far been killed. Unfortunately for us all, the same “reseachers” intentionally did just as slipshod a job as they did the first time around. What are the main problems? Well, for one the NY Times reports that the margin for error of the updated study  ”ranged from 426,369 to 793,663 deaths.†[...]
10:31 am
DEBATE OVER IRAQI DEATH COUNT
The Iraqi death count debate goes on and on and on and…. Liberals produce a figure much higher than conservatives. Of course, we know bad news turns into good news at the polls for Democrats. I said it before and
10:32 am
Posted by hammorabi yesterday:
Alert: the Iraqi capital is burning
Right now, the Iraqi capital is under very loud and continuous explosions and rocket attacks with huge fire and smoke in the south of the city.
The explosions believed to be due to explosion in big American weapon storages. There may be many causalities and the cause is not yet know.
The occupation of Iraq should come to an end soon.
In another recent post, hammorabi says:
The Failure of the Iraqi Example
Since the invasion of Iraq in 2003 until now the Iraqi security declined progressively and on the same time the terrorist organizations including Al-Qaeda became progressively stronger.
The number of Iraqis killed by the terrorist groups as well as the multinational forces is on the raise every month. Thousands of Iraqis killed each month by different ways. The number of crimes and corruptions everywhere in the systems is now out of control.
The US and other forces became easy targets to daily attacks especially in the West of Iraq. The number of US forces killed since then reached to 3000 soldiers. The MNF control has been lost completely on many areas including Ramadi, Haditha,Diyala and Falluja as well as other cities close to the Syrian border.
In November of ‘03 hammorabi was hopeful about the consequences of the U.S. invasion:
The New Iraq
After decades of hardship and suffering Iraqis everywhere must now unite to build a new free and democratic Iraq which contribute to the welfare of its own people and humanity at large …as it formerly did in its history.
You can’t dismiss hammorabi as a partisan hack, or writing to influence elections in the U.S.
10:38 am
I don’t believe Terrye exists at all. Obviously, since I don’t beieve he/she/it does not exist, it must be true.
Evidence in refutation, people. Might make you all a little bit more believeable.
10:49 am
Bogus Lone Study Claims Iraq Death Count Much Higher
This is just getting ridiculous. What’s said is the unbalance in the NY Times article make the AP’s article seem fair, though the fact that it’s pumping the story so heavily and without many comments from contradicting surveys makes their…
11:27 am
With all of the statistical expertise on display here, I look forward to the publishing of the definitive debunking of this study in a peer reviewed journal. Also, I can’t seem to find the one that addressed the 2004 Hopkins study. Do you know where I can find that?
By the way, it’s very cute how you and Fred Kaplan pretend not to understand basic principles of statistics. You are pretending, aren’t you?
11:37 am
Obviously, a leftist lie. Our President has told us only 30,000 Iraqi’s have died and we know he’d never lie to us because he answers to a higher Father. Praise the Lord and thank you Jesus for bringing freedom to the people of Iraq!
11:38 am
Man, this is totally ridiculous, and obviously partisan. In fact, I wouldn’t be surprised if this whole war was one big partisan hoax to discredit the Bush administration. I know Iraquis and they’re not dead. And you know statistics are just a way to lie with authority. Heck, even the methodology and terminology of statistical analysis is foreign—chi square? Isn’t that based on some Greek thing? And you know about those Greeks pederasts. If they could get up off the young boys for a moment maybe they could come up with ways to count actual deaths.
11:55 am
So let me get this straight: you bitched about the previous study because the sample size was too small and the margin of error too great. So they addressed all of those complaints, and came out with a new study. And now, in a flash of brilliance, you’re using the previous study, whose criticisms have all been addressed now, to say “See? They do bad studies, so this one’s bad too!”?
They just don’t teach enough logic in the schools these days, do they?
And, as for your second bitch, that the timing of the release is somehow suspect, I’d ask you this: if there’s information that will help the public decide whether their current leadership is performing correctly, do responsible people hurry and inform the population before the election, when it will be useful, or after the election, when it’s useless?
12:00 pm
[...] Rightwing Nuthouse [...]
12:08 pm
So.
How many Iraqi civilians have died? A dozen? Two? A hundred? A thousand? What is your limit I wonder? What number would make you sit there, self-satisfied and righteous that the Iraq invasion was still a good idea? Well whatever that number is let’s pretend for a second that it is in fact that correct number (I’m sure it just comes in under Saddam’s body count).
Do you see the violence ending anytime soon? Do you see being an Iraqi civilian getting any safer? Do you see an end to the civil war? The terrorism? The crime?
Do you see the point or are you so desperate to protect your fevered ego that four years from now when there are even more dead civilians and even more statistics describing the deaths you’ll still be spouting the same tired bullshit?
Iraq civilians are dead, America is responsible*, deal with it.
*No, no, I don’t mean that America deliberately targeting civilians calm down. What I mean is that because America invaded and occupied Iraq, Iraq’s security became America’s responsibility. Every time a civilian dies in Iraq at the hands of the terrorist America is ultimately responsible. Not fair? Guess you shouldn’t have invaded huh?
12:34 pm
Why doesn’t the drive by media report on the millions of Iraqis that are still alive?
Look, Iraq is no more dangerous than many large US cities.
And if it is, who cares? The Iraqis are the ones holding up the spread of democracy.
And if all of them were dead there’d be no more violence in Baghdad.
12:38 pm
[...] Like practically everybody else I’m very discouraged by the situation in Iraq. The deaths of ordinary Iraqis is unacceptably high whether it’s the 49,000 estimated by Iraq Body Count or the 650,000 reported in a recent study (which Rick Moran sensibly notes does not seem to distinguish among al-Qaeda, insurgents, and truly civilian Iraqis). [...]
12:43 pm
I’ve yet to really dig into the methodology yet, so my comments will be limited.
I do note that Allahpundit—whom I generally admire—does not understand what cluster sampling is, based on his reference to the sample being “not taken in areas where violence was ‘clustered’...” The study does use cluster sampling, and states it uses the same method as in 2004, though this time it does not appear at first blush that they re-clustered clusters as they did in 2004. Cluster sampling can be a valid method, but it has some very definite limitations, evidenced not least by the wide margin for error stated. Moreover, the baseline for the pre-invasion death rate is only 14 months, which nicely excludes any consideration of Saddam’s repeatead war crimes, which inflicted more than a few “excess deaths” on the Shia and the Kurds.
But before getting into the minutia of applied stats, let’s notice that one of the authors listed is Les Roberts. Roberts was also involved with the 2004 Lancet study. He presumably found the time to work on this one after withdrawing from the Democratic primary for the U.S. House of Representatives seat of the 24th Congressional District in Chenango County, NY, and before deciding whether to run for the state senate:
http://en.wikipedia.org/wiki/Les_Roberts_(epidemiologist)
And Ronald Waldman, the epidemiologist at Columbia University quoted by the WaPo and excerpted above? He’s a thousand-dollar contributor to the Roberts campaign, according to OpenSecrets. Before that he donated to Kerry and the DNC.
I would think that if you were trying to present an objective and scientific study, especially a month before the election, you wouldn’t have a failed Democratic candidate as one of the authors. But then again, the right wouldn’t be able to count on the press not mentioning it.
12:51 pm
George:
Fine, why not make it 6 million?
I am simply pointing out that there are morgues in Iraq, there are doctors in Iraq, there are communities in Iraq and no one has come up with any numbers that are even near this. Now the lefties will get all exicted because it serves their purpose, they could care less if it is true or not. The fact that it is absurd on its face means nothing to them. Reality is incidental.
If this is true then the suicide bombers have killed 84,000 people. Now considering the fact that if there is a car bomb in Iraq and it kills ten people reporters from all over the world do a story on it,do you think they just over looked all the others?
And a third killed by bombing raids, that would be about 200,000 people have supposedly died? Where? That is more people than Hiroshima, Nagsasaki and Dresden. I am simply pointing out that if they are going to claim all these people died then it should follow there would be some evidence beyond their pissy little survey. Like dead people. And graves.
I do know that when Saddam would fill a mass grave the liberal mass media just pretended not to notice, but as a general rule the media has not been nearly so forgiving of Bush as they were Saddam so it would seem to me they would have come up with some pics of hundreds of thousands dead in bombing raids.
After all the people who make the claim are the ones who are supposed to back it up. I know we never ask the UN and the Clinton people to back up their claims that Saddam had stockpiles of weapons of mass destruction and look where that got us. They just pretend they never said it. puhleaze.
My guess is this will just be spread all over the Arab media and will inspire more violence and will probably help get some more Americans and Iraqis killed but only we right wingers seemed to care about that. Gas on a fire is fine and dandy with the antiwar movement it seems.
As for whether or not this is all our fault, how about blaming Saddam? He could have done the same thing Kaddafi did and he would still be running his country. Or how about blaming the Democrats and the UN who would not give Bush1 support to go on in back in the first Gulf War and take Saddam out? If they had there would have been no question as to where the weapons were, no Food for Oil scam, no hundreds of thousands of Shia killed in uprisings, etc.
But then being a liberal means you never have to say you’re wrong or you’re sorry. You just preach and point fingers and make outrageous claims you can’t back up.
12:56 pm
salvage raises a more general question regarding the number of dead and US responsibility for the excess deaths. What the question ignores is that the nature of the violence now is largely sectarian violence—revenge killing resulting from a largely Sunni slaughter of Shia and Kurds over decades.
This is not a new phenomenon. The expulsion of Germans from Eastern Europe after WWII resulted in well over 10 million displaced persons, with estimates of those killed ranging from 500,000 to 3 million.
http://en.wikipedia.org/wiki/Estimates_of_number_of_deaths_in_connection_with_expulsion_of_Germans_after_WWII
Nevertheless, most people consider WWII to have been a success for the US and the world. And I have never seen anyone whip out a crying towel for the Germans on this point.
Similarly, the fact that the Shia—and to a lesser extent, the Kurds—are killing Sunnis is not a big surprise and something which history suggests was unavoidable—unless you were prepared to enable the baathist regime indefinitely into the future.
1:09 pm
The number seems highly flawed because we never heard reports of 100 deaths per day until the sectarian violence started (and this report is saying 500 deaths per day since DAY ONE of the invasion; how would that go unnoticed?).
Also, as others point out, many of those killed deserved to be killed. And, this “war” may have been inevitable; we may have only accelerated the process.
Much of the continued violence is totalitarians trying to prevent a transition to democracy. So, if it is immoral to initiate/cause these “excess” deaths by invading Iraq; then, wasn’t it immoral for our forefathers to start the Revolutionary War and cause “excess” deaths then?
1:17 pm
A large 95% confidence range is not necessarily a bad thing, if they state that it really is that large. Does it really matter if the number of excess deaths is 400,000 or 700000? It still is a lot. Also, I can tell you that the reason why the used 95% as their confidence interval is that if you have above 95% confidence in your results, they are called ‘statistically signifigant”. It was interesting thait the rate of NON-violent deaths was not statistically changed (p=0.528, I believe), which is a good control to have. It would have been really good if they had asked the families if they had taken the bodies to the morgues, or if they had the deaths reported in any way. Apparently 92% of the deaths were confirmed by death certificate, however. Anyway, I can’t see anything wrong with the paper, but I just use stats at work, I am not a statistician myself. I await better heads to evaluate it. The timing is not suspect, however. There is no doubt that it was timed precisely to be released now. The paper itself doesn’t seem wrong, however. Don’t reject it just because it says what you don’t want to hear, at a time you don’t want to hear it.
1:17 pm
“But then being a liberal means you never have to say you’re wrong or you’re sorry. You just preach and point fingers and make outrageous claims you can’t back up.”
-Damn straight Terrye. The endless search for the guarantee of one’s righteousness defines the liberal. (“Original sin? Come on, you Jesus hypocrites…”) Hating one’s own country, hating oneself, no matter. How else to explain a study that makes claims, with no serious evidence?
1:21 pm
It’s an 8 page paper, and quite readable. The margin of error is considerably lower than the margin of error for the 2004 estimate. The last page of the paper outlines the reasonable statistical reasons to doubt the conclusions.
Here
is the link again.
1:28 pm
[...] Right-Wing Myth–This study is a “pseudo-scientific hit piece” because it uses a methodology that expert statisticians right-wing bloggers think is bogus. [...]
1:36 pm
The answer is simple. No figures, reports, news, etc. in any way embarassing to either side should be allowed within six months of any election.
1:44 pm
1. The reort is bogus
2. It was released now by the terrorist-sympathizing,left-wing to embarass the current American administration.
3. All those Iraqis were actually killed by terrorists.
4. Bill Clinton is responsible for the 655,000 deaths, for the report being bogus and for releasing the bogus information now.
1:49 pm
If I were an antiwar liberal I’d be against the invasion of Iraq, preferring instead that Saddam had been left free to continue killing Iraqis at a rate the Lancet never addressed in those heady pre-war days. I’d also hope I never had to explain that to an Iraqi who had lost a loved one to Saddam’s mass graves, or his daughter to Uday’s appetites, or his village to a cloud of gas.
1:56 pm
In fact, the study makes absolutely no effort to differentiate between civilians and insurgents
They wouldn’t be insurgents if there wasn’t an occupying force, genius. They’d still be civilians. Or did you miss the entire point of comparison in the study?
2:01 pm
If I remember correctly went into Kosovo to stop a killer and yet that killer was not as bad as Saddam. The difference? The presdient had a D behind his name.
It is and was a safe bet that people would die in Iraq whether we went into that country or not, it is a violent place. So yes, the president was warned of that, he was also warned that Saddam would get back to wiping out the Shia and the Kurds and the Marsh Arabs as soon as he was free to do it. There were no shortages of warnings.
But this study is stupid. Here is an example why:
From 1940 to 1945 Bomber Command dropped 955,044 tons of weaponry on Europe(some of this was mines and the land total on Germany is less than this figure).
It conducted 391,137 sorties.
The area bombing campaign was by today’s standards indiscriminate bombing of cities.
593,000 german civilians died (AJ Levine, The Strategic Bombing of Germany 1940-1945, Prager, 1992, p.190) .
Think about that.
2:06 pm
Flypaper for innumerates
If you followed the debate over the first Lancet study you know that it featured numerous attacks on the study from folks who manifestly did not have a clue about statistics. The new study gives us much more of the…
2:08 pm
salvage
There’s nothing wrong decrying the fact that people die in wars. That’s a true fact. But the war ended in about six weeks. The rest is an insurgency part of which involves al Qaeda fascists with their car bombs and their backing and egging on the insurgency itself.
In case you hadn’t noticed, Islamo-fascists are and have been attacking and killing people around the world for years and years. They’ve been doing it since long before Iraq.
If we hadn’t gone into Iraq, they’d all be doing this in, guess where, Afghanistan! Then you’d be saying we shouldn’t have removed the Taliban.
If we didn’t fight back, we could only sit and wait for attacks. There’s not enough money and personnel in the world to protect all of America!
Yes, be sad for all the people who have died, but unless you offer yourself in their place, you have no choice.
2:13 pm
Margin of error? Did they mean 95% Confidence Interval? Surveys and polls have margins of error; statistical studies do not.
2:14 pm
What ever happened to fighting back intelligently?
2:15 pm
Our Wormtongues
The Washington Post reports this morning on a new study being released that claims that 650,000 Iraqis more have died since the March 2003 invasion of Iraq than would have if there was no invasion. That is more than 10
2:15 pm
600 000 dead? No one can hide or ignore that number of bodies piling up. 200 000 by bombing? – where is the evidence? Where is the evidence beyond some small survey – and surveys can be molded to fit one’s desired outcome as everyone knows; indeed they can be outright fraudulent – conducted by known Democrats and released a few weeks before an election? People still think that if you have Ph.D. after your name it is a mark of your truthfulness and not of membership in a victimary cult whose members have done so much to undermine their credibility with anyone who is paying attention to the universities. Did you see the scapegoating mob that went after Summers? And some group of expert survey takers has just ranked Harvard number one university in the world? Reality anyone?
People will give up their critical faculties, and they will give up a serious relationship to reality, if it fulfills their fantasy ideology which in turn mediates their existential angst that only grows with the lack of a working faith. And that is why it is only a matter of time before America really gets the kind of demon the left think George Bush is. Unless the real dragon is slain. Bring back the cross of St. George, bring back the Union Jack – America has gone bonkers!!
2:17 pm
If I were an pro-war conservative I’d be for the invasion of Iraq, preferring instead that terrorists, insurgents and criminals be left free to continue killing Iraqis at a rate the Lancet addressed in these endless war days. I’d also hope I never have to explain that to an Iraqi who had lost a loved one to terrorists, insurgents and criminals’ mass graves, or his daughter to terrorists, insurgents and criminals’ appetites, or his village to shock’n’awe or clean and hold or whatever they’re calling it this week.
See that’s a saw that cuts both ways, I’m under the impression that many of you don’t care how Iraqis die as long as Saddam has nothing to do with it.
Think about that.
Yeah, that different war from a different time, with different people for different reasons. I think that it has absolutely nothing to do with this war. I think if you need to look at the casualty rates of one war to make yourself feel better about another that you may have a problem.
But hey, you want to start talking past wars let’s talk Vietnam, let’s talk the first Gulf War and why it was a success and why this one is a miserable failure. Isn’t it interesting how different the casualty rates are?
Why don’t you think about that?
2:18 pm
Well, Toby, I think what has happened with this absurd ‘study’ is that the Left has finally jumped the shark.
Nobody will believe them anymore about much of anything.
2:22 pm
That’s a true fact. But the war ended in about six weeks.
You go tell that to the marines, you go tell them they’re not in a war.
Hahahahah! Oh my, too bad the other side doesn’t see it like that. Is that how you comfort yourself? We won! Why don’t they acknowledge that they lost?
As for the rest, flypaper bullshit. Afghanistan, guess where they’ve learnt all them IED tricks? Tell me all the time money and men poured into Iraq, they wouldn’t make a difference in Afghanistan? Seriously? Gettoutahere.
2:26 pm
Salvage
Yes, some of the jihadis learned new tricks in Iraq. SO DID WE.
Get a grip.
2:28 pm
Margin of error? Did they mean 95% Confidence Interval? Surveys and polls have margins of error; statistical studies do not.
Inexcusably sloppy language on my part, sorry. Yes, 95% confidence interval.
2:34 pm
salvage:
I care about how those people die. I care enough to know that fanning the flames by putting propaganda like this out there will only make it worse. And the people most intent on fanning those flames often as not are not even Iraqis. Iraqis are just cannon fodder for the left. Just like those poor people in Darfur. We all know what is going on there, what has been going on for years. Clooney and his ilk will posture and preen and act like they give a rat’s ass and demand that something be done. But if Bush sent in the military how long do you think it would be before we started hearing no blood for oil and seeing our soldiers portrayed as wanton killers?
We send those young men and women into harm’s way to difficult and dangerous work in dangerous places, it would be nice their fellow Americans did not treat them like cold blooded mass murderers. This kind of propaganda puts Iraqis and American servicemen in more peril because it feeds the antiAmerican Arab press and plays to the paranoia of the Arab political world. Way to go.
2:47 pm
salavge, in high dudgeon, ignores the historical example of “excess deaths” in post-WWII Europe. He really should be telling us what a spectacular failure the invasion of Europe was because of those excess deaths, how it just wasn’t worth it.
2:52 pm
BTW, the Gulf War was probably not considered a “success” by the hundreds of thousands of Shia and Kurds slaughtered and displaced by Saddam after the war. It was probably not considered a “success” by the tens of thousands of Iraqi kids who died as Saddam siphoned the oil-for-food money while Kofi Annan looked the other way.
salvage does not seem to care very much about those dead Iraqis, because he cannot try to pin their deaths on the Bush Administration.
2:56 pm
If? we sent in the military?
Are you living in some kind of time warp or something?
Face it folks, all these Iraqis are dying in a blatant attempt to make our president look bad.
2:59 pm
I’m an econometrician. I do sampling design, among other things, for a living. The biggest potential issues I see here are (1) whether the clusters were actually chosen randomly (there’s no real way to document this); (2) whether there’s overcounting of shared members from families spilling across households (selection of adjacent structures beginning with a randomly selected house); (3) whether the protocol for reselecting clusters deemed unsuitable post-selection has any impact on results.
Here’s my reaction to my own objections: (1) there’s no way to tell; (2) a search for duplicate death-certificate records would clear this up quickly if the researchers retained this documentation; (3) this might be a problem though some (three) of the clusters picked in lieu of the originals seem to have been dropped for “misattribution.” I’m not sure it’s documented how many (in total) of the original 50 clusters were subject to the protocol that allowed researchers to choose the next nearest population area instead.
I don’t like cluster sampling, as it results in less precision per fixed amount of sample and is highly sensitive to the representativeness of the units sampled, but I generally also have the luxury of recommending something else to my clients. What ultimately needs to be done is a study with a much larger sample and a more robust sampling methodology.
3:09 pm
I suppose I’d also be interested to see how the results would be affected if projected solely from the documented (i.e. certified) deaths. Validation of the household observations is terrifically important, since people could say anything they liked.
Household membership, etc., might also be subject to interpretation. Questions of interpretation of the data collection instrument often factor heavily into reported outcomes—as was certainly the case with the early Card-Katz-Krueger studies on fast food employment and the minimum wage. Payroll data on restaurants in the same ZIP codes as the respondents in the original study didn’t confirm the original phone questionnaire data at all. Just the opposite, in fact.
3:18 pm
(2) whether there’s overcounting of shared members from families spilling across households (selection of adjacent structures beginning with a randomly selected house);
This is the one that immediately bothered me as well. As you say, it should be easy enough to verify.
Re larger sample size;
A sample size
of 12 000 was calculated to be adequate to identify a
doubling of an estimated pre-invasion crude mortality
rate of 5·0 per 1000 people per year with 95% confidence
and a power of 80%, and was chosen to balance the need
for robust data with the level of risk acceptable to field
teams. Sampling followed the same approach used in
2004,8 except that selection of survey sites was by random
numbers applied to streets or blocks rather than with
global positioning units (GPS), since surveyors felt that
being seen with a GPS unit could put their lives at risk.
The use of GPS units might be seen as targeting an area
for air strikes, or that the unit was in reality a remote
detonation control.
3:33 pm
Apparently, this site’s proprietor is not interested in knowing the actual number of Iraqi civilian deaths, just undermining the efforts of those who attempt to calculate it.
3:40 pm
Davebo:
I am not the one living in the time warp, it is all those movie stars doing their power to the people shtcick living in a time warp. And yes, the people who run Sudan are going to go right on doing what they are doing because no one will stop them and if Bush even tried we can only imagine the screeching that would ensue.
For years I listened to people like Clooney bitch because the US supported dictators, the US takes a dictator out and they bitch even more. Now who is living in a time warp and who has shown the most indifference to the fate of the Iraqi people?
We have a bogus report but no bodies and the left gets indignanat and self righteous and yet when people find real mass graves with real remains of real dead Iraqis, the antiwar folks could care less.
3:40 pm
“A sample size of 12,000 was calculated to be adequate to identify a doubling of an estimated pre-invasion crude mortality rate”
Well, yes and no. Let’s not let “a sample of 12,000” become the meme here. The units sampled were households, and only 1800-and-something of those were sampled. Now, 12,800-plus people correspond to those households, but this isn’t the same as a random sample of 12,800-plus people because, within households, individuals share many of the characteristics that would be used to project to the larger population. One has to take account of the clustering in e.g. calculating standard errors of one’s estimates, lest the software think you have more unique observations than you do. The software they used, Stata 8, has good routines for complex survey data, so provided they set up the design metadata correctly prior to analysis, the numbers as calculated by the program are correct.
Let me pipe up with one more thing—clustering works best when, within a cluster, you have good heterogeneity. I’m not sure that picking a household from within a cluster and then going to all geographically contiguous households until you reach your quota of 40 gives you the heterogeneity you need. The incidence of violent death in this conflict might exhibit spatial correlation.
3:50 pm
655,000 Iraqi Deaths? 770 a Day? Prove It.
What to say about the study publicized this week claiming that Iraq’s ‘excess’ death toll has reached 655,000? Gateway Pundit notes that the figures are so outlandishly high as to be impossible:This latest Lancet Study released today claims that 555…
4:07 pm
Right I’m hungry so let’s make this quick…
Yes, some of the jihadis learned new tricks in Iraq. SO DID WE.
And what are those tricks? Seen the latest casualty figures for the coalition forces?
Do you even understand the nature of the conflict? Do you know what a massive advantage the terrorists have there? They don’t have a fraction of the training, resources or skills of the world’s most advanced and lethal fighting force and yet they manage to murder two to three coaltion soldiers a day.
Think about that.
Terrye I’m tired of people like you, I’m tired of you recycling the same stupid nonsense as if somehow reports of bad news magically puts terrorists in Iraq and guns in their hand. If you think that the violence in Iraq would magically disappear if people stopped noticing it than I can’t help you.I do hope one day you join reality and realize that people pick up guns for a wide variety of reasons. CNN is not one of them.
Karl I’m sorry I have one of these busted calendars that say the year is 2006 not 1943 and these stupid atlas and history books of mine insist that Iraq is not Germany. Weird huh?
And you don’t think the first Gulf War was a success because Iraqis died at the hands of Saddam rather than a mélange of terrorist groups, criminals and Marine crossfire? Gosh I’m sure even when Donald Rumsfeld was shaking Saddam’s hand on behalf of your government you were deeply concerned about Iraq’s human right’s record. I have no doubt that if we were to compare contributions to Amnesty International during that era that our checking accounts would sync right up.
Funny thing, the President Bush that wasn’t a miserable failure wrote this about why he didn’t go to Baghdad:
While we hoped that popular revolt or coup would topple Saddam, neither the U.S. nor the countries of the region wished to see the breakup of the Iraqi state. We were concerned about the long-term balance of power at the head of the Gulf. Trying to eliminate Saddam, extending the ground war into an occupation of Iraq, would have violated our guideline about not changing objectives in midstream, engaging in “mission creep,” and would have incurred incalculable human and political costs. Apprehending him was probably impossible. We had been unable to find Noriega in Panama, which we knew intimately. We would have been forced to occupy Baghdad and, in effect, rule Iraq. The coalition would instantly have collapsed, the Arabs deserting it in anger and other allies pulling out as well. Under those circumstances, furthermore, we had been self-consciously trying to set a pattern for handling aggression in the post-cold war world. Going in and occupying Iraq, thus unilaterally exceeding the U.N.’s mandate, would have destroyed the precedent of international response to aggression we hoped to establish. Had we gone the invasion route, the U.S. could conceivably still be an occupying power in a bitterly hostile land. It would have been a dramatically different—and perhaps barren—outcome.
Well thank goodness that didn’t happen!
4:10 pm
I’m a spatial analyst. To Dr. Steve’s first point, I do think they mitigate, but don’t eliminate, the problem of overlapping deaths by confirming that the deceased resided in the house for three months before the death. This presumably increases the threshold for determining residence, since it would lead to fewer people reporting the deaths of transient family members who live next door. It’s likely not possible to confirm this, though, because they did not record names of either respondents or deceased, given their IRB protocol.
With respect to spatial association, it is highly likely that the incidence of violent death is spatially correlated, for several reason. First, take the sectarian nature of at least recent stages of the conflict. We know for instance that Shiites and Sunnis living in mixed neighborhoods have been targeted in Bahgdad. There’s a spatial relationship. It is also likely, though I am only speculating, that roving bands of militants do not rove randomly, but target certain areas, perhaps those close by. There’s another potential spatial relationship.
The concern here is that both the overlapping deaths error and the spatial correlation error are likely to produce overestimated death rates. (All things being equal, they would also apply to the original 2004 study.) This would seem to undermine the tally of the study, particularly in the face of vastly different counts from other sources, which if not necessarily accurate themselves at least serve as a check for validity.
4:19 pm
Before arguing about the methodology, wouldn’t it be smart to ask if the findings are inherently plausible?
From Morgan at Flares: “How many car bombs were detonated in Iraq from June ‘05-June ‘06? How many people would they have to have killed, on average, for the total to have been 63,600 people? I would think that the number of car bombings would generally be accurately reported. If they killed (on average) 10 people each (which seems high based on the most recent car bombings reported by Iraq Body Count), that would mean 6,360 car bombings in 13 months, or 16 every day. Is there any data consistent with that? If not, there is reason to believe that the sample is biased.”
But of course the left doesn’t care about plausible reality. For them, reality is a construction of the powers that be. If we don’t like this present reality, we can wave the magic wand of “resistance”, and construct a new reality, just as the powerful hegemons who oppress us have constructed this reality.
Here’s an example, the celebrated Harvard political “scientist” Robert Putnam: “His research shows that the more diverse a community is, the less likely its inhabitants are to trust anyone – from their next-door neighbour to the mayor.
This is a contentious finding in the current climate of concern about the benefits of immigration. Professor Putnam told the Financial Times he had delayed publishing his research until he could develop proposals to compensate for the negative effects of diversity, saying it “would have been irresponsible to publish without that”.
[...]
Prof Putnam stressed, however, that immigration materially benefited both the “importing” and “exporting” societies, and that trends “have been socially constructed, and can be socially reconstructed”.
In an oblique criticism of Jack Straw, leader of the House of Commons, who revealed last week he prefers Muslim women not to wear a full veil, Prof Putnam said: “What we shouldn’t do is to say that they [immigrants] should be more like us. We should construct a new us.”
Construct a new us? Seriously folks, a lot of these professorial people are nothing more than magicians with an adolescent whine against “anomic” reality.
And the media trust such people to take a survey of reality? Guess what the MSM must think about reality? – it’s a construction of the government that it is their journalistic responsibility to deconstruct and reconstruct…
4:22 pm
wow. the neocon war on science continues unabated, don’t it? i think if they don’t like science they should give back all the medical treatment they get and all the convenient electronics they use- just for starters!
4:34 pm
salvage, the only saw that cuts both ways is the one the enemy would gladly take to your neck were the men and women you hate not out there protecting you and Iraqis at the command of the President you hate for the country you hate. You can twist others words, which is what leftist antiwar idiots do all day every day, but you can’t escape that you are felching for the enemy. I can face Iraqis with a clear conscience all day long because I support their cause for freedom, as opposed to you and your friends who hate Bush so much that you would have left them to Saddam. You can deny and attempt to deflect from that fact all you want, but you already wear it.
I suggest we ignore this unprincipled fool; he obviously treasures those high albeit fabricated casualty numbers because they feed his BDS.
4:39 pm
A new low in STUPIDITY and Insensitivity
You know, I can read about this, and understand why so many decent conservatives are abandoning Bush these days: SUZANNE MALVEAUX, CNN: Thank you, Mr. President. Back on Iraq, a group of American and Iraqi health officials today released a…
4:47 pm
Salvage:
I am tired of people like you too. I am tired of people who talk about international law, but don’t think that it mattered whether or not Saddam broke it daily. I am tired of people who talk about innocent people being killed when in truth they could care less about those people and have proved it time and again. And I am tired of people making outrageous claims they refuse to even attempt to back up. I am tired of people whining about how they got robbed every time they lose an election and yet they have no respect for the will of the people in a country like Iraq.They actuallly had an election, that should count for something.
This is not a question of refuting bad news. I am not saying the news of out Iraq is wonderful, but 550,000 dead in two years is insane. It is a bizarre claim.
Isn’t 50,000 bad enough?
4:59 pm
pos:
If this is just some neocon war on science, they they should not have any trouble proving their claims. After all scince is not just conjecture. It is based on fact, so where are the facts?
For instance, they say that 14% of the 655,000 people who died were killed by suicide bombers. That is over 91,000 people. That is their claim. Not mine. Now have any of the defenders of this survey ever seen anything that would back that up? I would say those victims were buried in Iraq and there would be death certificates for them and they would have families, so where are they? Who are they? Where and when were they killed? The survey offers no such eveidence. This is not science, this is propaganda.
5:03 pm
I see the new york slimes did not make any mention of Iranians,
Egypytians, Jordainians, ect. killed, just lump em in one big pile and a pile that seems way too big to me. If these PEACEFUL people would just live up to what they claim is in the PEACEFUL koran we’d all be much better off.
To you moonbats out there, you have lost this war here in America with your ignorant rants about TERRORISTS rights, ect.
Please just go to another site and rant.
5:49 pm
SpatialDan,
The concern here is that both the overlapping deaths error and the spatial correlation error are likely to produce overestimated death rates.
Why wouldn’t spatial correlation error also be likely to produce underestimated death rates?
DrSteve,
Well, yes and no. Let’s not let “a sample of 12,000†become the meme here.
Agreed. I was commenting more on the practical considerations. Sample size 12,000 and tight geographical clustering were chosen primarily to “balance the need for robust data with the level of risk acceptable to field teams” – the implied consideration is that the more the field teams roam, the more likely they are to be killed.
6:12 pm
[...] Rick Moran makes the same arguments, only a little more intelligently. The things he says that I haven’t refuted yet are, Someone is wildly off base here. Could it be the group that says that the US military has killed 180,000 Iraqis as a direct result of military actions? Gunshot wounds caused 56 percent of violent deaths, with car bombs and other explosions causing 14 percent, according to the survey results. Of the violent deaths that occurred after the invasion, 31 percent were caused by coalition forces or airstrikes, the respondents said. [...]
6:35 pm
“Why wouldn’t spatial correlation error also be likely to produce underestimated death rates?”
Offhand I don’t think I could speak to the direction of that effect. It would certainly muck up the SEEs even more, though.
6:45 pm
Why not just check the cemeteries? These people {if they existed at all} did not vanish. If that many died, at least a great many of them would have a record of burial.
What too mundane?
7:23 pm
Is this performance art?
You really did add up the percent of Iraqis killed by GSW and by Coalition Forces? Seriously?
I hate to break it to you, but sometimes Marines (brace yourself) use guns.
9:39 pm
[...] In a study conducted by The Lancet, journal of the British Medical Association, a figure of 650,000 Iraqi deaths is posited since the war began. [...]
10:53 pm
[...] A Newer World lists 5 wingnut talking points that we can expect, and dubunked them: 1. Right-Wing Myth–This study is a “pseudo-scientific hit piece†because it uses a methodology that expert statisticians right-wing bloggers think is bogus. [...]
11:54 pm
The Arizona Republic published the NY Times version today – 10/11/06: “Study: Violence has killed 600,000 Iraqis”, by Sabrina Tavernase and Donald G. McNeil. The last paragraph reads, “The U.S. military has disputed death figures provided by the Iragi government, saying that they are far higher than the actual number of deaths from the insurgency and sectarian violence, in part because they include natural deaths and deaths from ordinary crime.”
The “study” covers the period from March, 2003 to July, 2006 or about 1200 days. So what they’re trying to get us to believe is there’s been an average of 500 violent deaths per day over this 1200 day period.
Today’s Republic obit pages show that Maricopa county had between 60 and 70 deaths. Maricopa county has a population of 3.8 million people, Iraq has a population of around 26.8 million or 7 times Maricopa county. Do the math. If there’s an average of 60 deaths per day in Maricopa county, 7 times that is 420 Iraqi deaths per day from natural causes, assuming the same death rates per equal population. That leaves an average of 80 deaths per day that could be attributed to violence, or 96,000 over the 1200 day period. But the natural cause death rate is probably quite a bit higher, so the correct number of violent deaths is probably down around the 30,000 the U.S. Military claims.
2:30 am
Wingnuts Attempt to Debunk Iraq Deaths Survey
The Liberal Avenger
Some people think that it’s best to just ignore the unpleasant stuff
A study (link) published in Lancet, arguably the most prestigious medical journal in the world, estimates that the Iraq war has caused 655,000 Iraqi deat…
3:36 am
Oh dear, Doyle (and others). Never mind your version of the math. Why not start by reading the words first? The 655,000 is the number of EXCESS deaths over the 1200 day period, not the total number of deaths.
It’s telling that you would launch into your debunking attempt without actually thinking through the study properly. Whether you believe their conclusion or not, you must take the time to understand what the number signifies and how it was calculated before you can start to find fault with it.
3:51 am
“The well respected Iraq Body Count, run by academics opposed to the war, lists nearly 49,000 civilian dead since the invasion. Their methodology is sound and their numbers are based on actual reports from morgues, the media, and the military.”
Well respected and, without a shadow of a doubt a massive undercount.
From IBC : “Casualty figures are derived from a comprehensive survey of online media reports and eyewitness accounts. Where these sources report differing figures, the range (a minimum and a maximum) are given. All results are independently reviewed and error-checked by at least two members of the Iraq Body Count project team in addition to the original compiler before publication.”
It is absurd to imagine that this method will produce anything other than a vast undercount. It should be obvious to all that media reportage from Iraq is patchy at best, so their count must be patchy at best.
IBC provides a bare minimum count. Simple as that.
“Color me suspicious, but if the study had come out 3 weeks after the election, I would be more sanguine about the author’s motives.”
I’m curious about this one. As far as I can tell there is nothing wrong with the methodology with this study. The sample is significant (and a carefully chosen sample at that), the error bars are clearly published, the caveats are clear. If, for political reasons, people don’t make it clear that this is a mortality study then it is hardly a fault with the research, just with the presentation by others.
It seems to me that a well informed populace is vital for democracy to work. Why would you want this study delayed until it cannot affect people’s ability to make a judgement, because the time for judgement would have passed?
Would 600,000 excess deaths be an acceptable number for bringing democracy to Iraq and ridding the world of Saddam? What sort of figure would you say was reasonable for that goal?
3:57 am
“He really should be telling us what a spectacular failure the invasion of Europe was because of those excess deaths, how it just wasn’t worth it.”
The invasion of Europe was a spectacular failure. And the people who invaded lost eventually and were tried in War crimes courts for their culpability in those excess deaths.
5:45 am
How the Washington Post got the Foley ‘scoop’
Ever wondered how the Washington Post got word that Rep. Foley was sending inappropriate messages to pages? Well, stop scratching your head and wonder no more. Our intrepid reporters have out-investigated the mighty WaPo sleuths. To do so, they attac…
5:56 am
Drongo:
Is hating Bush worth looking like an idiot? It appears so.
This is the same bunch of ninnies who accused the Clinton administration of killing 547,000 Iraqi children with sanctions. But then the invasion came and all of a sudden pre war Iraq was heaven on earth. According to them only half as many Iraqis died before the invasion as were dying in Europe at that time. Peaceful Europe with its good health care system.
Since this is excess deaths we are talking about they have to compare the death rate before the invasion with what they claim to be the death rate after. If I remember correctly they put the death at about 5.5 per 1000, which is half of Europe’s. That right there makes the study bogus.
6:44 am
Saying that a statistical method is “well-established” is one thing; showing that it’s an appropriate method for the data is quite another.
Here’s an example: Vector autoregression is a “well-established” econometric technique. But you can’t use it on every single time series you encounter (you have to examine integration properties first). I’d suggest that using contiguous-household sampling to study the incidence of violent death in a war zone is a bad fit for the data, even if the overall sampling design is the “well-established” clustering method. To knock that application isn’t to deny that the technique is well-established, it’s to suggest that nearly every statistical technique relies on a series of distributional and other assumptions, and using them when these assumptions are violated can get you into trouble.
8:40 am
“’Gunshot wounds caused 56 percent of violent deaths, with car bombs and other explosions causing 14 percent, according to the survey results. Of the violent deaths that occurred after the invasion, 31 percent were caused by coalition forces or airstrikes, the respondents said.’
The fact that those three percentages totalled up equal 101% isn’t as ridiculous as 31% of deaths were caused by coalition forces or airstrikes.”
Congratulations—this will likely be the dumbest thing I will read a conservative saying today, and it’s not even 10AM.
Could it be that neither “deaths caused by gunshot wounds” nor “deaths caused by explosions” are mutually exclusive from “deaths caused by coalition forces”?
Perhaps it would be a good idea to learn how to draw a bloody venn diagram before you go wading into epidemiological critique. Par for the course when it comes to Bush supporters, I suppose…
9:01 am
Yr. Fthfl. Svnt.
Wow, that answers none of my points! Ha
Ha! Yes it’s because I hate Bush that he’s screwed everything up! Me and reality and about 60% of Americans! We all hate America!
Terrye
International law huh? So you think that the U.S. should follow it? A big supporter of the UN are you? I’m surprised! So I guess you think America should invade Israel to enforce the various international laws they’ve broken? Like using cluster bombs on civilians? Or are you a bit more selective, one of those who only get puffed up about the law when you like what it’s saying? Cuz here’s the thing Sparky, under international law the invasion of Iraq WAS ILLEGAL. See with no WMD there was no threat to the U.S., no threat to U.S. no legal rational for war.
And I am tired of people making outrageous claims they refuse to even attempt to back up.
Um… report… backs it up… numbers, statistics, sources… did you read it ?
>respect for the will of the people in a country like Iraq
Majority of Iraqis want the Coalition forces gone or is your respect for the will of the Iraqi people as adjustable as your support for international law?
>They actuallly had an election, that should count for something.
Ah yes, a few in fact and to have them they had to shut the country down and they’re still under martial law. Their “government†is hidden in a fortress because if they ever met in a half-public venue they’d be massacred. That’s quite a stable democracy Bush has made there, you should be very proud. So no, it counts for nothing because Iraq is a war zone and the Iraqis are targets and that “democracy†is about as stable as Mel Gibson at a Bar Mitzvah with an open bar.
>550,000 dead in two years is insane. It is a bizarre claim.
Do you even understand the report? It’s not saying that 550,000 Iraqis died in specific ways, it’s saying 550,000 Iraqis have died since the occupation from everything to degrading infrastructure, disease, infant mortality, natural causes as well as the violence. It’s an overall snapshot of a country that is collapsing under the weight of an endless civil war. It’s neither bizarre nor surprising. You just don’t like it so you’re deciding that it simply cannot be true. That is called denial and it is neither helpful or healthy.
Now let’s say that for a second the numbers are true, I’m not saying you have to believe that, let’s just pretend that you have been given rock solid, indisputable proof that the numbers are complete and accurate.
Would this change your support of the invasion and occupation?
I think the majority of you would still be “Rah! Rah! Goooo Dubya!†because the alternative is something you simply could not handle; Bush has screwed everything up and y’all helped him along.
But thank Jesus, Budah, Allah, Zeus, Odin and Bill Hicks that the majority of Americans have finally woken up and realized what many of us knew a long time ago. GW Bush is and will always be a miserable failure.
Y’all are a minority, enjoy!
9:41 am
The thing is it does add up: We’ve dropped 240,000 cluster bombs. We’d be fools to think they didn’t kill anyone. Add in gunfire and car bombs and 600,000 dead doesn’t seem that big.
If you don’t like that, consider this. They interviewed 1,840 random people and found over 500 dead (92% of those showed the death certificate). And if you think about they clearly couldn’t interview at homes that don’t exist anymore…so 1 dead for every 4 randomly slected home. That’s bad no matter how you look at it.
10:23 am
I’m waiting for one statistical expert to tell me that the methodology of this study is bad. Somebody step up, or shut the hell up.
My understanding is that the point of the study is NOT to state an exact number of people killed. The point is simply to get a comparison of death rates before the war and after. From that you can say whether things have gotten better or worse. If worse, how much worse. Again, why is this methodology bad?
Even if the timing of the release of the study is politically motivated—and I’d like to see proof of that, too—when did conservatives turn into such wimps about political debate prior to an election? Or should we disregard everything that comes out of any member of the Bush administration’s mouth as politically motivated as well?
11:12 am
xii:
“I’m waiting for one statistical expert to tell me that the methodology of this study is bad. Somebody step up, or shut the hell up.”
Please see my numerous posts above. Maybe you don’t think I qualify as an expert (PhD in Economics from a top-10 school, took every econometrics class offered, plus 10 years experience working with complex survey data).
Open minded Engineer:
“so 1 dead for every 4 randomly slected home. That’s bad no matter how you look at it”
Reread the study. Only the initial home in each cluster was randomly selected. The others were contiguous to that home. That’s not an innocuous detail. Spatial correlation would mean that the probability of deaths in one household could affect the probability of deaths in other households in the same cluster. Look at how fish & wildlife does its bird count cluster surveys—if they start with a randomly selected observation point, they move a specified minimum distance away before setting up the next observation point. There are multiple reasons for doing this, some of which aren’t relevant to the study we’re discussing (birds are easier to double-count than people) but spatial correlation is a big consideration.
11:43 am
DrSteve, the location of each cluster was also randomly selected, no? The reason for the contiguity was legit—“By confirming the survey to a cluster of houses close to one another it was felt the benign purpose of the survey would spread quickly by word of mouth among households, thus lessening the risk to the interviewers.” But even if we grant your concern as a given, does that invalidate the study’s findings? Are you saying that the method used here likely resulted in grossly misleading findings?
12:28 pm
Yes the clusters were allegedly randomly selected. My comment goes to nonrandom data collection within the cluster (beyond the selection of the first home), and the general requirement for heterogeneity within clusters if one’s going to get all one needs out of having selected that methodology.
I understand there’s a stated reason for the protocol, but the sampling math doesn’t care whether it’s a good reason or not.
I guess I’m just going to have to do an illustrative simulation at some point, but my intuition is that spatial correlation of war deaths results in overstatement of counts under this methodology. The rationale is that types of deaths are not spatially independent—finding one increases the probability of finding another next door. I’m less sure about that than I am that the confidence intervals understate the actual standard error of the estimate here, but in any event I don’t have a whole lot of confidence in their number.
I shouldn’t have to jump up and down and shout about “grossly misleading findings” or professional misconduct, should I? This subject is a big deal. I’m trying to maintain some gravity here.
12:48 pm
This blog posting and many of the winger comments here are just hilarious. What’s with you people? If the cause is just, what do you care how many people die? Right? Is it 150,000? 300,000? 500,000? Some of those bombs, bullets, what have you, had to hit somebody. To make an omelette, you gotta break some eggs. Well, here’s an indication that a lot of eggs got broken. Why such outrage at the number?
As some one else said here, what number of actual, confirmed, no question about it, deaths caused by our adventure in Iraq would cause you to change your mind about it?
1:11 pm
“I shouldn’t have to jump up and down and shout about “grossly misleading findings†or professional misconduct, should I? This subject is a big deal.”
I very much agree that it’s a big deal. What I’m interested in knowing is whether you, as a professional in this field, think that this study’s results are likely too high. And, how likely, and how much too high. In other words, is the study worthless? And, since it’s likely that this kind of study has been done before on other subjects, are they also worthless?
1:42 pm
Terrye. There is a very good reason why the baseline death rate in Iraq should be lower than Europe—the age of the population is also much lower.
In England in 2005, 16% of the population was aged 65+. 83% of all deaths occured in this group which is a rate of 49.5 per 1000. The overall death rate for all ages was 9.6 per 1000.
In Iraq, only 3% of the population is aged 65+. If just 3% of the English population was 65+, the overall death rate would be 2.1 per 1000. So by comparison, a death rate of 5.5 per 1000 in Iraq seems to be reasonable or even on the high side.
You could have figured this out for yourself if you had considered for a moment before crying “bogus”. Thinking before commenting might someday save you from looking like an idiot too!
2:52 pm
Anyone who refutes this study should go and do their own. THe best way to refute a scientific study is with your own. Surely the state department has an interest in showing how this study is BS. Why don’t they fund their own, using the same accepted methodologies, but ensuring that the sampling is done fairly?
When the right has actual data, and not just “It’s biased!” as an argument, people might pay attention.
3:15 pm
I believe it. It’s not enough to say, “Those numbers don’t sound right.” The way that you refute what someone says is with facts, not your opinion. Furthermore, people who don’t understand statistics shouldn’t comment on statistics. If you don’t know what a confidence interval is, don’t convince the world that you are an idiot by expounding on how little you understand of it.
3:17 pm
What I’m interested in knowing is whether you, as a professional in this field, think that this study’s results are likely too high.
Yes.
And, how likely, and how much too high.
Maybe very difficult to say. In statistics, we have formulae to use as tools, but these formulae are generally based on assumptions. Once those assumptions are violated, we depart from the nice formulae and sometimes the impact is hard to describe without re-deriving all the metrics from scratch. I know that’s unsatisfactory, but there it is.
In other words, is the study worthless? And, since it’s likely that this kind of study has been done before on other subjects, are they also worthless?
I would look askance at any study that geographically concentrated data collection where spatial correlation was an issue, particularly if it relied on a method where heterogeneity and independence of those data were important. But I’m not going to be baited into a blanket statement about cluster sampling. Legitimate methods can be applied to data that violate the assumptions required to use them.
Anyone who refutes this study should go and do their own. THe best way to refute a scientific study is with your own.
Maybe the best way, but certainly not the only way. I can evaluate a study, in many cases, by reviewing the data, the methods and assumptions used, even the batch files written to process the data. All of which I’m asking Burnham for. I’ve audited federal studies where the researchers used the wrong “weights” option in their software. I didn’t need to re-perform the study from scratch to know their report was wrong.
And let’s not let this devolve into a chickensurveyor argument, OK?
3:20 pm
Face it—the kooky righties will dance and backpedal until you finally interview all 600,000 dead people. I’ve stopped wasting my breath on the dead-enders who still support this bloody quagmire and this failed president. They are so out of touch with reality that it’s like trying to convince a psychotic that their delusions aren’t real. Come to think of it, it’s EXACTLY like that.
3:27 pm
You sound a bit closed-minded yourself, I’m afraid.
3:29 pm
“According to them only half as many Iraqis died before the invasion as were dying in Europe at that time. Peaceful Europe with its good health care system.”
Do you have a source for that, out of interest?
4:03 pm
[...] Rick goes on: There are other sources for counting Iraqi dead. The well respected Iraq Body Count, run by academics opposed to the war, lists nearly 49,000 civilian dead since the invasion. Their methodology is sound and their numbers are based on actual reports from morgues, the media, and the military. Their number of confirmed dead is still less than half the number estimated in the 2004 Lancet study. (Emphasis is mine, admin) (link) [...]
7:09 pm
All of which I’m asking Burnham for.
Out of curiousity, have you had any response from Burnham?
7:44 pm
the last thing I want to do is get into a calculus of death. however, for anyone who thinks that the number is “too high to be credible”:
a sample of deaths in world war I(combined civilian and military, rounded off)-
France: 1.4 million
Italy: 650,000
Romania: 611,000
Russia: 3.7 million
Serbia: 1.1 million
UK: 733,000
United States: 126,000
Austria-Hungary: 1.5 million
Bulgaria: 350,000
Germany: 2.5 million
Ottoman Empire: 2.5 million
What were they saying again about the death toll being too high?
8:28 pm
Following Up on the Lancet Study
As expected, the Lancet study on civilian deaths in Iraq has created a firestorm on the net. What frankly astounds me is how utterly dreadful most of the critiques of the study have been. My own favorite for sheer chutzpah…
2:24 am
DrSteve:
I fully agree with you that the clustered sampling is not as good as a truly randomized sampling would be (in terms of tightest error bars for a given number of samples). But I fail to see why this methodology would either over- or under- estimate the death toll. If there is spatial correlation, it’s true that you’re more likely to find deaths close to other deaths. But you’re equally likely to find survival close to other survival. Hence, there is no push one way or the other, from what I understand. There is probably a reason it’s called “spatial correlation”, not “spatial bias”.
As an aside: It bothers me that people are willing to accept a concrete “lesser evil” like killing Iraqis over a completely imaginary “greater evil” like the WMD bogeyman, and that somehow this gets passed off as “logic”. Doesn’t matter how logical and rational you are: Garbage-in, garbage-out. Seems considering uncertainty in decision making is too abstract and difficult for some people’s minds (especially those used to spoon-fed religious dogma).
Salvage: I loved your post 48.
8:28 am
Jurgorr:
As I’d noted, it took me a long time to come to the conclusion I did, and I was pretty uncomfortable doing even that, but the more I think about it the more I think that spatial correlation “looks” to the statistical calculations the way any other strong within-cluster association would: Like a lack of variance in the underlying data.
The phenomenology for the homogeneity is different from other patterns we observe in clustering, say, children of the same case-head sharing environmental factors, but I think the result is probably the same—the large SEEs we already see.
Their method isn’t a first-best, but I’m no longer sure it overstates anything—unless, as I’d also noted, the death certificates weren’t unduplicated across households.
So this is me stepping back from my earlier statement to xii.
2:18 pm
I’d be very hesitant about trying to place much interpretation on figures for car bombing. To begin with, we are talking about 38 reports, only 13% of total deaths, so the margin for error in extrapolating to the entire country will be very large. Moreover, while the investigators were able to verify most death reports by examining death certificates, they have no independent way of confirming the accuracy of third party reports as to the cause of death, and a lot of the respondents probably don’t have direct knowledge of what happened. So the cause of death statistics are probably more useful for telling us what the Iraqi people are blaming for the loss in life than for telling us what is actually the case.
8:01 pm
[...] Right Wing Nut House discusses the study, including quoting the people who are supporting it as saying “there is very, very little reliable data coming out of Iraq.†[...]
10:44 am
“The fact that those three percentages totalled up equal 101%...”
EricT is correct. This is one of the most idiotic things I’ve ever heard. One of the other most idiotic things is EricT’s explanation. The real explanation (as any baseline literate math student could tell you) is called ROUNDING ERROR.
Your actual percentages are always equal to 100%. In this case, the actual percentages might have been as follows:
55.5 percent gunshot,
13.9 percent explosion
30.6 percent aistrike
(Note that these percentages add up to be 100%)
But when you ROUND those numbers for a news report, you write “56 percent gunshot, 14 percent explosions, 31 percent airstrikes”. Seriously, this happens very frequently with every type of statistical survey. It is complete illiteracy to imply this makes the study less credible.
1:32 pm
I sent Dr. Burnham a very polite request for his study data, protocols, stat programs and log files. He wrote me back within 2 hours but demurred citing a busy schedule and the desire to protect both his surveyors and the sampled neighborhoods. Both are totally understandable points but really don’t extend to everything I asked for—he could have an RA e-mail me his .do files in 5 minutes. I’ll ask him again in six months.
8:32 am
Terrye wrote:
“I am simply pointing out that there are morgues in Iraq, there are doctors in Iraq, there are communities in Iraq and no one has come up with any numbers that are even near this. . . I am simply pointing out that if they are going to claim all these people died then it should follow there would be some evidence beyond their pissy little survey. Like dead people. And graves.”
This is idiotic. They went over and searched as much as they could in a war zone, used totally sound sampling methods and statistical practice and got these numbers. At this point the crucial thing is not that it would be possible (with more resources) to be more accurate—of course it would!—but that this is the best estimate existing, far better than anything the Iraqi government has.
Denial is not just a river in Egypt.
8:39 am
Dr. Steve wrote:
“The rationale is that types of deaths are not spatially independent—finding one increases the probability of finding another next door.”
Just as not finding a death decreases the chance of finding one next door. Unless they deliberately started out with a home they knew someone had died in, there is every bit as much chance of this giving too low a result as too high.
8:44 am
Terrye wrote:
“For instance, they say that 14% of the 655,000 people who died were killed by suicide bombers. That is over 91,000 people. That is their claim. Not mine. Now have any of the defenders of this survey ever seen anything that would back that up? I would say those victims were buried in Iraq and there would be death certificates for them and they would have families, so where are they? Who are they? Where and when were they killed? The survey offers no such eveidence. This is not science, this is propaganda.”
What idiocy. The survey is their evidence! They checked death certificates. All the above amounts to is the demand they do more—well, of course we would have more confidence in the results if they did even more research, but they did the research they could, and these are the results. Terrye certainly has no better research to point to—he simply doesn’t want to believe these results because they are troubling to his conscience.
Terrye, when someone tells you that 6 million Jews died in the Holocaust, do you demand the person digs them up and shows you the remains?
12:53 pm
Not only are American scientists wildly exaggerating the number of deaths in Iraq despite our peace-keeping efforts there, but the Iraqi government is making things look bad when actually everything there is fine and getting better.
According to the Iraqi Health Ministry, the rate of deaths attributable to the insurgency in August was essentially the same as in July—somewhere around 50 corpses delivered to the city morgue each day.
But U.S. military spokesman, Major William B. Caldwell, (CNN, September 11) reported that there had actually been a 52 percent drop in violent deaths in August as compared to the previous month.
As he pointed out, the Iraqis were erroneously including people killed by explosions and bombings. According to Major Caldwell such deaths are not due to violence and should not be so counted.
Let us hope that the American administration will take immediate steps forcing the Iraqi Health Ministry to correctly report the rapidly decreasing number of truly violent deaths in their capital.
As for those scientists, our new law signed by President Bush allows them to be jailed indefinitely since they are obviously aiding and abetting terrorism.
5:51 pm
[...] A BN bud – not of the same ideological bent as BN, but an interesting cat nonetheless – has cited that Lancet Iraqi-civilian-death figure of 650,000 in a few places in some recent comment threads. Here’s where that assertion starts to unravel. [...]
6:30 am
while the investigators were able to verify most death reports by examining death certificates, they have no independent way of confirming the accuracy of third party reports as to the cause of death, and a lot of the respondents probably don’t have direct knowledge of what happened. So the cause of death statistics are probably more useful for telling us what the Iraqi people are blaming for the loss in life than for telling us what is actually the case.
info
10:49 am
As an aside: It bothers me that people are willing to accept a concrete “lesser evil†like killing Iraqis over a completely imaginary “greater evil†like the WMD bogeyman, and that somehow this gets passed off as “logicâ€. Doesn’t matter how logical and rational you are: Garbage-in, garbage-out. Seems considering uncertainty in decision making is too.
good!