I really don't know where to begin with this anti-Lancet piece by Michael Fumento. Should I start with the way Fumento describes Kane's paper as "so complex" that it "may cause your head to explode" while being utterly certain that Kane has demolished the Lancet study? Or with his assertion that I've been ignoring criticism of the Lancet study? Or with the way he quote mines me? Or that after again and again arguing that Lancet was wrong because they included Falluja when they should have left it out, he is embracing Kane's argument that they were wrong because they excluded Falluja? Or with a picture of a rake?
Ah heck, let's look at the quote mining:
Upon including the Fallujah data, Kane concluded that as incredibly wide as the confidence interval was as given, it now became so wide "that the lower bound is negative." This means the figures the Lancet came up with are not of statistical significance and therefore, in statistician lingo, "don't count for squat." ...
Lambert, in his blog, after three years of blasting critics of the Lancet study, conceded, "I would suggest that [Kane] has proven that this confidence interval is wrong," indeed, "obviously so."
Fumento makes it look like I was referring to the confidence interval for excess deaths, but look at my full comment:
[Kane's] argument turns on the CI for the post-invasion mortality rate (including Falluja) of 1.4-23.2. I would suggest that he has proven that this CI is wrong (as it obviously is, since there is no way the mortality rate could be below 4) rather than that the risk ratio CI is wrong.
Notice how he couldn't have quoted any more of it without giving the game away.
Now for his charge that I have "ignored" his arguments against the Lancet study. Let's see. Fumento says:
Further, the researchers used death certificates but didn't feel bound by them -- interviews were fine. "In the Iraqi culture it was unlikely for respondents to fabricate deaths," they wrote. Sorry guys, but I've reported from Iraq three times and I've written that interviewing Iraqis is essentially worthless because "they just tell you what they think will prove advantageous to them."
I dealt with this almost three years ago: 81% of those asked produced death certificates. There is little scope for invented deaths in the study.
Then Fumento has this:
The 100,000 figure is allegedly the excess over pre-war Iraqi mortality, which they claimed was 5.0 per 1,000 people annually. That was a fabrication absolute vital to the overall calculation. According to the CIA World Factbook, the pre-invasion (2002) rate was over 20 percent higher at 6.07 per 1,000. Remember, the study was allegedly looking for excess mortality; therefore the lower the authors set pre-war mortality the higher the excess post-invasion mortality looks.
I must confess not have rebutted this one before. But that's because last time round, Fumento offered this:
The alleged 100,000 deaths were those above the pre-war baseline. That baseline was predicated on a figure of 5.0 deaths per 1,000. BUT the figure for the US at the time was 8.3 deaths per 1,000. Obviously Iraq was one of the safest countries on the face of earth prior to the Yankee imperialist invasion. In fairness, the CIA Worldbook uses a 5.6 per 1,000 figure for Iraq but what was it's source? Saddam's ultra-trustworthy government, of course.
So, in rebuttal to his new argument, I would suggest that the CIA number is unreliable. And if Fumento wants to dispute this, he should take up with the guy who said that the number could not be trusted. Which was one Michael Fumento.
Back to Fumento's latest attempt:
Consider, too, that 100,000 deaths during the survey period meant an average of over 180 a day, of which the Lancet attributed a majority to airstrikes. Have you heard anyone claim our airstries [sic] killed over 90 civilians on any one day during the entire course of the war?
The Lancet did not attribute the majority of the 100,000 deaths to air strikes. The 100,000 number excludes Falluja, which was where most of air strike casualties were.
Fumento:
Anti-war and anti-American groups even said the Lancet figure was ridiculous. The website iraqbodycount.org estimated at the time about 14,000-16,000 deaths since the war began, a figure that even now ranges from about 68,000 to 74,500. The Evil One himself, bin Laden, in his pre-election video, made reference to the Iraq war and stated "over 15,000 of our people have been killed."
The Iraq Body Count is not an estimate of the total number of deaths. It just counts the number reported in the media. Not every death is reported in the media. No doubt the IBC people will be emailing Fumento and asking him to correct his mistake. Osama bin Laden's "over 15,000" does not contradict the Lancet number at all. Does Fumento not realise that 100,000 is "over 15,000"?
(Hat tip: Russel Seitz.)
Isn't it a tad cruel of you to make fun of a guy who looks like [this](http://www.bigfatblog.com/images/fumento.jpg)?
Quick, where is the Clorox for my eyes???
Linking to that image was more than a tad cruel, Robert.
Fumento will probably never be adequately mocked. An Olympian hack, with a vanity and belligerence exceptional even among self-appointed pundits, blindingly wrong about each and every subject to which he has turned his pen, and unable to recognize a fact when it's sunk its teeth into his cheek, Fumento has put himself beyond ridicule.
And yet, taking up his ice axe and crampons, Tim seems determined to scale Fumento's Himalayan buffoonery, whatever it takes. All I can say is don't try it without oxygen, Tim! It's suicide, man!
Clearly, Fumento's assertion that Kane's high-level math "may cause your head to explode", just like Malkin's claim that it is "mind-numbingly complicated", is an underhanded way to blame Kane for a pre-existing condition.
Sortition wrote:
It's interesting that Fumento doesn't mention that it took 191 posts in that thread for David to reveal that he didn't know how to calculate a CMR.
Kane's high-level math "may cause your head to explode"
Apparently there is a new (and superior) measure for the validity of statistical arguments.
If an argument makes your head explode, you know it's superior -- or at least you would have known, if your head had not exploded.
Fumento writes: *For the most part, [David Kane's] critics pretend to be dispassionate defenders of proper statistical analysis*
Well, I really was a dispassionate defender of proper statistical analysis. I swear! I'm disappointed to learn that all Kane's other critics were just pretenders. Still, despite what I now know was rampant deception, it seemed to me that a lot of valid criticisms were raised.
Reading Fumento so you don't have to:
...
...
Who was Fumento citing there? - himself.
...
...
A fine, fine read is The American Spectator.
So, in essence, Michael Fumento's sources for his argument are the CIA, Osama bin Laden and himself?
I have seen people been given the run-around, but not by their own earlier claims.
You would think that analyzing a war would demand a modicum of longterm memory. But denialists always manage to come up with new ways of making small kittens cry.
"You would think that analyzing a war would demand a modicum of longterm memory"
Prosecuting a war, too...
But no such luck.
It would seem that Iraq and Afghanistan are not the only places people have been embedded.
Robert writes:
Do you know how to calculate a CMR, Robert? If so, tell us the magic formula. Better yet, use the data that Tim has so kindly posted to replicate the result published in L1. (Note that they did not use a bootstrap for that calculation.)
As far as I know, no one has replicated that result. I think that it could be done (probably depends on how you weight the different clusters) but it would be a step forward for science if you would.
If you can't, then I would suggest that we are in the same boat on this topic.
Would the Joint Statistical Meeting (or its journal, if it has one) accept a paper from you, Tim? Or do they only take papers from war supporters?
David Kane wrote:
David, David, David. Of course I can show you, and of course we're not in the same boat on this topic. But if I do this, will you admit that this is a serious blow to your argument? And if so, will you write to Malkin and Fumento and tell them this?
Well, you could start by admitting you were wrong yet again, but that's like admitting the sun rises in the east and sets in the west. Assertions such as that Iraq Body Count's figures are probably somewhat low hardly accounts for the massive difference between their data and the Lancet's. (By the way, Iraq Body Count is clearly anti-war and therefore not likely to downplay the data.) But here's a nugget I offer you. A Huffington Post blogger who is as innumerate as you, has employed a rather, um, strange formula to conclude that over a MILLION Iraqi civilians have been killed. Now you can say, "Hey, let's just split the difference between reality and Huffington!
Fumento is now calling Tim innumerate?
Good one.
But at least Fumento does know the sun rises in the east and sets in the west (though I wonder how many times he checked that one on wikipedia before he posted it)
"Again, the [Roberts estimate of the] death rate in Iraq per capita is about the same as in Bosnia for the same length of time. Are we expected to believe that the Iraqi civil war has been a kinder, gentler war with 1/10 as many casualties as the Bosnian civil war?
Of course, the same folks telling us that are the same folks who up to recently were denying that it was a civil war, and up to the first Lancet paper were denying the IBC numbers as being unrealistically high."
http://scienceblogs.com/deltoid/2007/01/why_are_people_surprised_about…
Thank god you're OK, Mr Fumento! I was worried that David Kane had caused your head to explode.
"Assertions such as that Iraq Body Count's figures are probably somewhat low hardly accounts for the massive difference between their data and the Lancet's"
This much is true - it is of course that the IBC only uses deaths reported in the media that accounts for the massive difference.
I don't know about anyone else, but Kane's math causes my head to spin.
Perhaps that's a precursor to explosion...kinda like a centrifuge. If you get it spinning fast enough, it tears itself apart.
While Troll Lambert pretends he's just taking issue with Iraq Body Count's mortality figure, he's actually taking on the antiwar group itself and its powerful critique of the Lancet's "methodology" in a report from last October. Among them, the Lancet "655,000 dead" 2006 study would have us believe that:
"On average, a thousand Iraqis have been violently killed every single day in the first half of 2006, with less than a tenth of them being noticed by any public surveillance mechanisms" and that "over 7% of the entire adult male population of Iraq has already been killed in violence, with no less than 10% in the worst affected areas covering most of central Iraq . . . "
The press release concludes:
But Troll Lambert has never shied from from extremeness or improbability, and he's definitely shown an extreme aversion to rationality. Some people occasionally step on a rake; others slam themselves in the head with one several times a day whether they need it or not.
This would be the same IBC report that concludes that "Substantially more deaths have occurred than have been recorded so far, but their number still remains highly uncertain."?
What is thoroughly distasteful is that warmongers like Fumento believe that quibbling over how many tens of thousands of Iraqis we have murdered will make their war any righter! What a proud boast it is, that we "only" murdered a hundred thousand civilians en route to achieving a failed state and the demolition of America's global reputation and internal liberties.
Dr Zen, your phrase "how many tens of thousands of Iraqis we have murdered" is dishonest and manipulative. The vast bulk of violent deaths in Iraq have not been due to weapons fired by the U.S. or other MNF-I personnel. The bulk of violent deaths are due to attacks by various factions within Iraq - murders and bombings. Non violent deaths are contributed to by attacks on doctors, hospitals, police, and infrastructure that affects community health. The U.S. invasion of Iraq enabled this to happen, so they are "excess deaths as a result of the invasion of Iraq" and relevant to assessment of the ethics, competence and outcomes of the invasion, but they cannot reasonably be called murders by the U.S.
Thank god you're OK, Mr Fumento! I was worried that David Kane had caused your head to explode.
Here I thought that Tracy Spencer had done away with him! I am glad to see that you are OK Mr. Fumento.
Michael Fumento's head is even fatter than his rump and consequently more target-rich for me.
Does anyone else here remember the Kenny Everett skit about the guy who can explode his own head? Hilarious.
David Kane, calculating a CMR from the data you provide in your lancet data set is trivial. You can do it with any log-linear regression model. It's disturbing that you think you can criticise this paper and yet not know how to do that calculation.
And don't you see the harm you have done, running half-cocked into an analysis you don't understand? All the usual suspects have picked up your head-explodey, and now we're all being coated with whatever gunk inside their skulls passes for brains.
Now that's projection from the Fume. Good to know that his irony receptors are still non-functioning.
Throw in the usual mixture of appeals to self-authority, self-contradiction, canards, ad hominem and misquotation, and you've got yet more hackery from the hackiest of hacks. Still, we know why he continues to earn a living: it's hard work ensuring that your standards don't slip upward.
[Fumeto has replied](http://www.spectator.org/dsp_article.asp?art_id=11935) to a letter from Roberts and Burnham. Highlights are the way he presents a news story in Science about the urban death islands criticism of the Lancet study and tries to make it look like the critism was published in Science. And this bit of cluelessness:
>We are told that, for whatever reason, it's okay to consider a third of the data a "statistical outlier." That would be like releasing a "national poll" comparing the top Democratic and Republican nominees that excluded respondents in New York, New Jersey, and California. If the findings become useless by including Falluja, then so be it. If researchers can't collect the data they need, they should admit it rather than taking what they do have and pretending it's enough.
Haha, a purported magazine (is that David Brock's old stomping grounds, home of TrooperGate, Scaife and Ted Olsen's Arkansas Project?) actually publishes Fumento? He reminds me STRONGLY of "Ed Anger" in the Weekly World News. It's like the worst, most illiterate, most abusive, dishonest, insulting, shaggy-dog-story-rambling, never-made-it-through-high-school-science-or-writing-classes, most clueless possible blog comment troll - ever - and he gets to write articles? This is probably good, in a sense - keep people like this front and center as spokestrolls for the war .
And pretending Science had the criticism as an actual entry reminds me of Aaron Russo's overwrought fakeumentary "America: From Freedom to Fascism" being "shown at the Cannes Film Festival" in the sense that he rented an area of the beach and showed it to fifty people at the same time as the real festival nearby was showing real movies.
Why does it seem that my country (The US) is overrun by the musclehead types?
I mean, we have one running Caleeflowernia, for God's sake.
People here seem to spend too much time developing their body and too little time developing their mind (if they have one).
Tim Lambert wrote:
Ah. That reply is evidence for two things:
1. [Fumento](http://www.bigfatblog.com/images/fumento.jpg) hasn't yet figured out that Kane's paper is about the Roberts article, for which the cluster-level data have long been available.
2. We must add [Fumento](http://www.bigfatblog.com/images/fumento.jpg) to the list of "critics of mortality studies who do not know how to calculate a CMR".
Speaking of which: paging David Kane! Paging David Kane! For a guy who criticizes others for not responding to you, don't you think it's a tad unseemly not to respond to me?
>Some people occasionally step on a rake; others slam themselves in the head with one several times a day whether they need it or not.
Just so we're clear, MF, which one are you?
davidp, they were living, the US acted, they are now dead. If you want to call it manslaughter, that's fine.
Posted by: Michael Fumento :
"Assertions such as that Iraq Body Count's figures are probably somewhat low hardly accounts for the massive difference between their data and the Lancet's."
Lie. If you'd read the article in the Lancet, you'd realize that they discuss undercounting associated with media reporting.
"... (By the way, Iraq Body Count is clearly anti-war and therefore not likely to downplay the data.)"
Lie - they have. When the first survey came out, they ignored their own prior statements about undercounting.
"But here's a nugget I offer you. A Huffington Post blogger who is as innumerate as you, has employed a rather, um, strange formula to conclude that over a MILLION Iraqi civilians have been killed. Now you can say, "Hey, let's just split the difference between reality and Huffington!"
And ther are right-wingers (bloggers, administration officials) who've come out with ridiculously low death estimates. So?
Apologies for the delay.
1) In response to my request that he demonstrate how to calculate a crude mortality rate using the data from L1, Robert writes:
No. Whether or not you or I can replicate L1's CMR has nothing to do with whether or not my paper is correct. My paper takes the CMRs provided by L1 as given.
Anyway, it seems clear to me now that you are bluffing, that you can't demonstrate the steps that the L1 authors went through to provide, say, the pre-invasion CMR of 5.0 (95% CI 3.7 -- 6.3). If you can, then prove it. Help all of us understand the paper better. Tim has kindly posted the (cluster-level) raw data.
Again, I am not denying that this can't be done. Who know? Perhaps even you can do it.
I was just looking at implication 2 of Iraq Body Count's refutation of L2, the one linked by Michael Fumento up above. Whatever one thinks of L2, I think IBC inadvertently demonstrates the weakness of any argument based on official statistics.
IBC says the Iraqi MOH counted 60,000 wounded in the period from mid 2004 to mid 2006. The early 2007 poll funded by the BBC, ABC, USA Today and others
http://news.bbc.co.uk/2/shared/bsp/hi/pdfs/19_03_07_iraqpollnew.pdf
found that one household out of six had suffered at least one casualty from the "violence that is occurring at this time", whatever that means exactly. But it seems to indicate a much higher casualty rate than 30,000 wounded per year unless casualty rates went up by an order of magnitude or more right after mid-2006.
My link didn't work. I'll try the BBC link instead--you can click on through to the poll.
http://news.bbc.co.uk/2/hi/middle_east/6451841.stm
David Kane wrote:
Me, bluffing about knowing how calculate a CMR? [Ouch, that hurts](http://www.demog.berkeley.edu/courses/fall2006courses.html).
David, what a fascinating example of hubris. You do not know how to do something, so you conclude that no one else can either. However, that something "seems clear to you" has, once again, led you down the wrong path -- though for you
this seems about par for the course.
As you ought to have known long ago, we are clearly not "in the same boat." The reason you ought to have known this long ago is that you have had in your possession the proof of what I have been saying -- but with the blinders you're wearing you couldn't see it. 20 months ago, I showed a [graph](http://anonymous.coward.free.fr/misc/roberts-iraq.png)
with the cluster CMRs; more
remarkably, 14 months ago and then again one month ago, both times in response to your own requests, I have pointed you to [my code](http://anonymous.coward.free.fr/misc/iraq.r) in which
can be found the "magic formula" for calculating the pre- and post-invasion CMRs. Perhaps you missed it since the calculations were cyptically and misleadingly labeled "pre-invasion CMR" and "post-invasion CMR"? I leave getting the overall CMR from the cluster CMRs to you as an exercise.
I, and others, have warned you that you have been confounding the estimates of CMR and the estimates of the CIs around those estimates. You keep saying that my estimates of the CMRs and excess mortality depend on bootstrapping. They do not. The proof is in the code you ignore. You keep saying that Roberts' estimates of excess mortality depend on normality. They do not. Despite your exegesis of the rest of the article, the proof is at the
bottom of the left hand column on page 3, where the CMR calculation is given. Look at it, and please (please!) recognize that it does not depend on normality.
So this is what it comes down to: the estimates of excess mortality don't depend on normality, but your argument does, and there is no evidence that Roberts and Garfield made that assumption. You have done this even though there is no evidence for it and, in fact, there is evidence against it.
Your argument is a phantom argument. There is nothing there. This is what Tim Lambert meant when he said that all you've shown is that assuming normality for the CI including
Falluja is wrong.
David, there are legitimate criticisms of the Roberts and Burnhams articles. Yours isn't one of them. Your
paper is trash, and you're hurting yourself. Do the right thing. Write Malkin and Fumento and tell them you didn't know what you were talking about. Tell them you apologize for the exploded heads. You can even tell them you're working on yet another crazy argument. You don't have to tell them that you accused a demography professor of not knowing how to calculate a CMR.
David Kane: "Anyway, it seems clear to me now that you [Robert] are bluffing, that you can't demonstrate the steps that the L1 authors went through to provide, say, the pre-invasion CMR"
I wonder if Einstein went through a similar exercise back in 1905 -- hanging out at the university coffee shops looking for physics professors who might give up some of their insight into relativity:
"I bet you can't do that calculation on the length contraction, Herr Lorentz...."
"Hmm, well, that's all very well and good, but double or nothing that you can't determine the relationship between mass and energy."
" Zen, your phrase "how many tens of thousands of Iraqis we have murdered" is dishonest and manipulative. The vast bulk of violent deaths in Iraq have not been due to weapons fired by the U.S. or other MNF-I personnel. The bulk of violent deaths are due to attacks by various factions within Iraq - murders and bombings."
How do you know how many deaths are caused by the US? Setting aside L2 (which found a high fraction caused by the US), there are occasional estimates in the press that the US is killing roughly 1000 insurgents per month. Judging from what has happened in other guerilla wars,, that suggests the possibility that a large number of civilians are also being killed by US forces, though not reported as such. There were also stories back around early 2005 of US training of Iraqi units that were clearly going to be death squads, and even one or two references to a "Salvador option". So some of the death squad killing may have a US connection.
JB wondered:
Hmmm. I'm not sure your analogy is quite apt.
Robert,
Exactly.
Robert,
As I've given this more thought, I've come to the conclusion that David Kane is, in fact, correct. I'm grateful that JB mentioned Einstein, because the answers will only be clear to those who have a background in quantum mechanics. What we are looking at is a mortality crisis of unknown scale. The scope of excess death is indeterminate; thus, we can refer to it colloquially as Schroedinger's Catastrophe. Kane has demonstrated that we cannot discard the null hypothesis that the invasion of Iraq saved lives.
I realize, of course, that several people here have argued that Kane's model makes no sense, based on that fact that it postulates the existence of clusters with negative crude mortality rates. This, however, is only a problem for those who do not understand quantum mechanics. Considering the implications of Heisenberg's uncertainty principle, we must remember that there is no reason that Schroedinger's Iraqis cannot be simultaneously dead and alive. Quantum mechanics indicates that a single entity can occupy two physical locations simultaneously; thus, dead Iraqis in the Falluja cluster may indeed appear spontaneously in other clusters. Those of you who have ridiculed Kane's "zombie army" are merely displaying your ignorance of physics.
I must admit that I myself did not grasp this initially. Kane's analysis showed a decreased lower bound for excess mortality; but it also showed an increased upper bound. Kane insisted, however, that it was really only the decreasing lower bound that was important. When I asked him why the lower bound was more important than the upper bound, he did not reply. I was a bit disappointed; I would have treasured an actual quote. ("I give good quote," Kane once said.) In any case, I don't blame Kane for not responding; after all, the answer should have been obvious. A decreasing lower bound means more living, and fewer dead; and we must ascribe a greater weight to the living, since by virtue of living, they are not decaying; decay, after all, will decrease the weight of an object. Ergo, a decreasing lower bound carries more weight than an increasing upper bound. Clearly, the concept of indeterminate decay is central to the Schroedinger thought experiment.
I would like to point out a few other implications of Kane's research. Examine the graphs on P.9 of Kane's original paper; you will immediately notice a crest on each of the three illustrated curves, giving the appearance of a surging wave. This clearly demonstrates that the surge is working.
I realize that what I have presented here is perhaps counterintuitive. Because it has become apparent that many of the Lancet's defenders do not really understand the nature of crude mortality, when I have time, I'm going to work on a program to combine the most salient parts of Kane's and Fumento's critiques. I'm going to call it Schroedinger's Concatenator. It will intertwine the points raised by those who are able to understand the math (Kane) and those who are unable to understand it (Fumento). The result of this concatenation can subsequently be referred to as the Kane and Unable Critique.
Regards,
Bruce
Bruce: You owe me dry cleaning costs for the spilt coffee when I started to laugh.
On the other hand, in your Schroedinger's Concatenator can you please include all the points raised by exploding heads.
Looking forward to my $6.25!
John
Bruce:
You're very, very good.
Bruce;
Just one question of about Kanetum Mechanics.
What does the QM "collapse of the wave function" correspond with in this case?
The collapse of the Iraqi health care system? The collapse of the Iraqi government? The collapse of the Iraqi economy? The collapse of the Iraqi population? A superposition of all those?