Kane and Lancet

There has been more discussion at Crooked Timber on David Kane's criticism of the Lancet study. In response to Tim Burke's comment:

Good faith skepticism starts with, "Ok, I want to look at why you're making this claim, and your evidence for it. I don't want to take anything on faith." Not, "I'm sure you're wrong, because the results you're reporting aren't convenient for my political views and for my common sense understanding of things."--e.g., refusing to take seriously someone else's findings because of a particular conviction or faith in an opposite finding.

Kane replied with:

I think that this is quite unfair as a description of what I have done. I came to this story in 2004 as an interested bystander. I had no priors except a generalized skepticism of applied work which just barely rejects the null hypothesis. I sought to replicate L1 and was stymied by the authors. They refused to share their code. They refused to share the data at a detailed level (as they eventually did with L2). Les Roberts was, to put it simply, quite rude.

However in 2005, before he had asked Roberts for the data, Kane commented:

Allow me to raise one. The central problem with the Lancet study was that it was conducted by people who, before the war started, were against the war, people who felt that the war was likely to increase civilian casualities and who, therefore, had a expectation/desire (unconscious or otherwise) to find the result that they found.

I think that sort of a thing could be a big problem with cancer research as well.

On his own blog David Kane wrote:

One of the more annoying tendencies of Lancet defenders is that they refuse to recognize the breadth of academic criticism against the Lancet papers. Over time, I hope to gather some of that criticism together. Here is one example.

He quotes Fritz Scheuren

The recent controversy over the estimated Iraq war deaths that appeared in the October 11, 2006, issue of The Lancet has drawn considerable statistical attention to the situation in Iraq, as the results in the article did not appear credible. As mentioned by Gray, a follow-up to The Lancet piece occurred at a February session of the Washington Statistical Society (WSS), organized by Wendy Rotz, with talks by Asher and David Marker. The jury is still out on The Lancet results. Statisticians must assess the process used, not the outcome. But there is a lot wrong with the process, leading to the conjecture that the results are most probably wrong.

Scheuren does not tell us what he thinks was wrong with the process, but this does not annoy Kane.

Also, commenter Sortition has started a blog to explain what is wrong with Kane's work.

Kane implicitly attributes posterior distributions to the parameters being estimated in the Lancet paper - CMRpre, CMRpost, and RR. He then interprets the 95% confidence intervals stated for those parameters as covering 95% of the mass of those distributions. This reflects a fundamental misunderstanding of frequentist statistics, and of CIs in particular.

Finally, Kane emailed with a suggestion that he offer:

"A $100 prize to the person who can replicate the estimates and
confidence intervals for crude mortality rates, relative risks and
excess deaths as published in L1 using the released cluster-level
data."

I'm really not really that interested, but if you think this would be a worthwhile exercise, let me know in comments.

Tags

More like this

The AP's Paul Foy reports on the American Statistical Association meetings discussion on the Lancet studies: Number crunchers this week quibbled with Roberts's survey methods and blasted his refusal to release all his raw data for scrutiny -- or any data to his worst critics. Some discounted him as…
Daniel Davies summarizes what is wrong with David Kane's criticism: The mathematical guts of the paper is that under certain assumptions, the addition of the very violent cluster in Fallujah can add so much uncertainty to the estimate of the post-invasion death rate that it stretches the bottom end…
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…
Like David Rind over at Evidence in Medicine I'm a consumer of statistics, not a statistician. However as an epidemiologist my viewpoint is sometimes a bit different from a clinician's. As a pragmatic consumer, Rind resists being pegged as a frequentist or a Bayesian or any other dogmatic…

David Kane writes, "The central problem with the Lancet study was that it was conducted by people who, before the war started, were against the war..."

Were against the war? And Kane? Where was he perched as he writes these words? Certainly not in any bombed out pulverized and destitute Iraqi cities where hope was lost long ago... It seems to be fine to 'support war and agression' as long as 'we' are pulling the trigger. Chicago-based writer Paul Street sums it up when he says "..."The Bush administration and its many enablers used 9/11 as a false pretext for launching what most of the world knows to have been a monumentally illegal and significantly oil-motivated invasion of that country". In my view, those relentlessly attacking the Lancet study are the armchair imperialists who support Kane's exercise in futility. I'd like to ask Kane and his ilk this: How many corpses need to pile up in Iraq to signify that the policy was and is wrong, bankrupt, and vile? Irrespective of what the Lancet says, when are you going to admit that the war was sold on completely fraudulent grounds and is a monumental, mass-murderous war crime?

By Jeff Harvey (not verified) on 13 Sep 2007 #permalink

It's sloppy to call it the Lancet Study, they mostly just published it. Johns Hopkins - AMERICAN - and not exactly a hotbed of leftism or pacifism - took the lead role and people from Iraq and a couple other nations were co-sponsors.

Calling it the Lancet study is almost like calling something published in JAMA the JAMA study or in Nature the Nature study or in Science the Science study.

By Marion Delgado (not verified) on 13 Sep 2007 #permalink

Looks like IBC and David Kane have some more bad news to contend with; The ORB polling agency has conducted research which has indicated that up to 1.2 million iraqis have died as a result of violence since 2003:

Q How many members of your household, if any, have died as a result of the conflict in Iraq since 2003 (ie as a result of violence rather than a natural death such as old age)? Please note that I mean those who were actually living under your roof.
None 78%
One death 16%
Two deaths 5%
Threedeaths 1%
Four+ deaths 0.002%
Given that from the 2005 census there are a total of 4,050,597 households this data suggests a total of 1,220,580 deaths since the invasion in 2003.

Wonder what kind of endeavour they will undertake to rubbish the "ORB" Study...?

Oh, and you can read the press release here
Unsurprisingly, it doesn't look like we're seeing much coverage of this development in the MSM

So now David Kane is offering 100 dollars to anyone who will do his homework for him. Has Harvard sunk so low that there are no consequences for that sort of conduct?

Hint for any programmer out there who is so far down on his/her luck that s/he is willing to prostitute his/her talents for a lousy hundred bucks: you can write a crude but effective bootstrap in Visual Basic in less than fifty lines. Whether the lazy kid with the cash will actually cough up on delivery I don't know. Given his form so far I doubt it.

By Kevin Donoghue (not verified) on 13 Sep 2007 #permalink

Tim,

Aren't you guilty of selective quotation in the above? The full quote (and I believe that this was my first public comment on the topic) was:

jre claims that, with regard to the Lancet student, "not a single valid objection [has] been raised against its methodology or its results."

Hmmm. Allow me to raise one. The central problem with the Lancet study was that it was conducted by people who, before the war started, were against the war, people who felt that the war was likely to increase civilian casualities and who, therefore, had a expectation/desire (unconscious or otherwise) to find the result that they found.

Consider the Iraqis who did the actual door-to-door surveying. Do you think that they appreciated having such a well paying job? Do you think that they hoped for more such work? If you were them, would you be tempted to shade the results just a little so that the person paying you was happy?

Consider a counter-factual world in which the Pentagon (or the AEI or the Heritage Foundation) did a study with exactly the same methodology, sampling plan and so on. If that study had shown 100,000 fewer deaths, would you have been as quick to believe it?

Again, this objection in no way invalidates the study. But don't pretend that valid objections have not and could not be made.

In context, this seems as true now as it was then. In fact, it was even prescient! The interviewers gave Roberts et al what Roberts expected to find and, sure enough, Roberts hired them again two years later.

Again, the point is not that this alone is evidence of anything. The point was that reasonable objections could be made. No study is perfect.

Also, I think you are missing a "not" in "Scheurer does tell us", but perhaps I misunderstood your point.

By David Kane (not verified) on 14 Sep 2007 #permalink

David, why are you constantly evading the real issue about the carnage in Iraq, the result of an illegal, murderous invasion? I still don't even know what the aim of your futile exercise is. Is it to vindicate the war? Is that remotely possible for anyone with functioning brain cells? Let's say the actual death toll in Iraq - now estimated by ORB (see postings above) to be over 1 million since 2003 - was actually 300,000. Let's say there weren't 2-4 million refugees who had fled the country to Syria and Jordan but 1 million. Let's say 75% of the doctors had not fled the country but 50%. David, would you see this as a moral victory? How much Iraqi blood has to be spilled and how much of that nation destroyed for you to condemn the invasion for what it is? C'mon David, stop beating around the bush and tell us all.

By Jeff Harvey (not verified) on 14 Sep 2007 #permalink

Jeff, I think David is simply interested in the math. And by your example, why not report that there were a billion deaths and four billion refugees, if the correctness of the numbers doesn't matter?

"David, why are you constantly evading the real issue about the carnage in Iraq, the result of an illegal, murderous invasion?"

I like how you care so much about the pre-war carnage that Saddam was responsible for against his own people. Something that was never going to end in Saddam's lifetime. Why do you have so much against the possibility of Iraq having a future? Sure it will cost in lives now, but that's how it works very often with dictators.

"Jeff, I think David is simply interested in the math"

I think the Crooked Timber thread and the Deltoid threads suggest that is not the case. Kane seems more interested in debunking the claims in the Lancet studies than he is in the math. The math is simply a line of attack he finds convenient, given his background.

Scheuren, not Scheurer.

richard wrote:

The math is simply a line of attack [David Kane] finds convenient, given his background.

How many disturbing things do you guys count in that sentence?

In context, this seems as true now as it was then. In fact, it was even prescient! The interviewers gave Roberts et al what Roberts expected to find and, sure enough, Roberts hired them again two years later.

David, i guess you are somewhat new to social science research. in short, most people start their research and polls, with a thesis in mind.
quite often, the research will support their thesis. and yes, some of them will rehire those who worked for them before hand.

so you are after a HUGE thing there!
please after reforming the way that a CMR is calculated, reform the way science is done! no thesis, before you start research. no cooperation with people, who worked for you in the past!

Again, the point is not that this alone is evidence of anything. The point was that reasonable objections could be made. No study is perfect.

i have seen very few reasonable objections to the study. none from you.

but i d love to see a list of those!

Jeff, I think David is simply interested in the math.

that s why he decided to share with Malkin immediately?

I like how you care so much about the pre-war carnage that Saddam was responsible for against his own people. Something that was never going to end in Saddam's lifetime. Why do you have so much against the possibility of Iraq having a future? Sure it will cost in lives now, but that's how it works very often with dictators.

there s a BIG problem with your view:
if these estimates are correct, then MORE iraqi civilians were violently killed after the invasion, then under the entire reign of Saddam!

I like how you care so much about the pre-war carnage that Saddam was responsible for against his own people. Something that was never going to end in Saddam's lifetime.

I like the slippery slope Ben wants to dance on:

It's OK! OK, I say! to invade sovereign nations if they do things we don't like. The Soviets didn't like all the Central Americans we killed. The Chinese didn't like all the folks we killed by selling someone gas. Guess it's OK to invade America then, according to Ben's logic. And that One Child policy? Let's invade China in retribution for all the fetuses killed that could be Wal-Mart shoppers.

Da! é¼çç, Ben?

пÑивеÑ,

D

Ben, Iraq has a future? Under permanent US occupation? Hee hee ha ha ho ho ho!!! Please let me pick myself up off the floor. Let me be brutally frank: The US and UK didn't give a damn about Iraqi civilians when they bombed the civilian infrastructure of the country to kingdom come in 1991, sanctioned the country for 12 years, killing hundreds of thousands more, then launched their murderous 2003 invasion through 'shock and awe' with bunker busters, cluster bombs, depleted uranium and daisy cutters. As Noam Chomsky quite correctly observed recently, the 'civilized west' view those who get in the way of privilige and power as 'unpeople' - like ants on the sidewalk that you step on routinely but inadvertently as you walk to the store. The Iraq war is just another example of part of the global war of the privileged few against the excluded many. When Margaret Thatcher scolded members the Labour Party in the UK in 1987 for condemining the Halabja atrocity in Parliament, she said, 'Saddam is a man with who we can do business'. When a Clinton aide called Suharto, one of the world's biggest torturers and mass murderers 'Our kind of guy' in 1996, he summed up long-term US foreign policy. Human rights, democracy, freedom, etc. etc. do not figure. They never have. The fact is that the whole global economy is being structured to support < 20% of the planet's population (e.g. the rich). Then rest are 'forever expendable'. The truth is that barbarism, violence and mass murder are standard practices on 'our side', only 'we' use different technology to carry it out.

Finally, its about as low as one can get to suggest that those criticizing US and British foreign policy in Iraq somehow 'supported' Saddam Hussein. I thought that this turkey had been put to bed years ago, but apparently not. Its strange, Ben, how much collective amnesia you appear to have. Who armed Saddam to the teeth and in full knowledge of his crimes? Who continued to grant the tyrant export licences, and to give him diplomatic cover long after his worst crimes were carried out? The only reason he fell out of favor with Washington and London was the same old story: he slipped the leash. Like Manuel Noriega, who committed his worst crimes on the CIA payroll, Saddam became a liability when he became too uppity and in his case invaded Kuwait. The US demands 'stability' (e.g. obedience) from its client tyrants and Saddam's regime became unstable. Had he not invaded Kuwait, I am sure that the US and UK would have supported him to this very day, like they did with Suharto until almost the bitter end.

By Jeff Harvey (not verified) on 14 Sep 2007 #permalink

Finally, its about as low as one can get to suggest that those criticizing US and British foreign policy in Iraq somehow 'supported' Saddam Hussein.

I never suggested any such thing. I only pointed out that it's not as if Iraq was a paradise before the invasion, and further that it had zero prospects for the future, for whatever reason. It is very well likely "our" fault that it is that way, but blame aside, it was what it was.

It's OK! OK, I say! to invade sovereign nations if they do things we don't like.

When is sovereignty trumped then? Is there anything a sovereign nation could do, as long as it was only internal, that would lead you to call for invasion? What if the sovereign nation in question was beheading all the homosexuals in their country. Oh wait, they already do that. Well, what if they were beheading all the liberals? Or would it be bad to invade them, because they are sovereign?

There is a perversely fascinating symmetry to David Kane's view of the Johns Hopkins team and his own style of prosecution.

Above, he supplies the full text of his first comment on the Irag mortality study, apparently thinking that "in context" it is clear that he started out with no axe to grind -- he just wanted to point out, as a valid objection to the study's methodology and / or results, that its authors were against the war. Does it even need to be said that this argument is utterly wacked? Apparently it does, because David Kane clings to that argument today. In the CT thread, Tim said it best:

That sort of thing is a big problem with cancer research as well.

In my view, that comment pretty much disposes of the "bias" argument. But, hell, let's pretend that David Kane's position -- that accusing a researcher of bias constitutes a valid objection to his methods -- is something a thinking person ought to spend ten seconds considering. How could Roberts et al. ever be cleared of that charge? Do they have to hire a buffer group with no opinions for or against the war to do all the data collection? Do they have to promise their field team that they will never be hired in future studies? Swear in affidavits that no bounties were given for higher mortality numbers? What?

David Kane cannot lose on this one. If he stumbles onto a problem with the math, great! If his statistical analysis is exposed as incompetent posturing, he can play the innocent novice and beg for education. If he is confronted with the fact that every one of his complaints about the two mortality studies has been factually empty and transparently agenda-motivated, he can always fall back on argumentum ad neener neener: "Yeah, well, your guys were always against the war, and can't be trusted, so you're another." Thus the symmetry.

okay Ben, I like your logic. when do we invade Saudi Arabia? I presume we don't have to do a risk analysis first, to see if our intervention will make things worse? Let's go!

"A $100 prize to the person who can replicate the estimates and confidence intervals.."

Kane has "gone fishing" (again). He couldn't get Robert to bite, so now he has baited his hook to see if there are any chumps out there who will..."

I wonder what kind of fish Kane expects to catch for $100. Crappy?

Marion delgado: It's sloppy to call it the Lancet Study, they mostly just published it.

And their editor, Richard Horton, wrote articles championing it in the Guardian newspaper, and spoke on the back of it at anti-war rallies.

Jeff: Who armed Saddam to the teeth and in full knowledge of his crimes?

Overwhelmingly the USSR, France and China.

Tim: I think that sort of a thing could be a big problem with cancer research as well.

Well, I do think that if some cancer researchers appear to be diagnosing more cancer than actually exists, then they probably shouldn't be working on that project.

Well, I do think that if some cancer researchers appear to be diagnosing more cancer than actually exists, then they probably shouldn't be working on that project.

That, however, is not an accurate analogy to Kane's statement, which is that their METHODOLOGY is suspect because of their anti-war views.

Now, since you blew that, is there any reason to pay attention to anything else you might post?

> Jeff: Who armed Saddam to the teeth and in full knowledge of his crimes?

> Overwhelmingly the USSR, France and China.

Convenient right-wing myth, but no.

SIPRI, the source for your figures, says:

> The Arms Transfers Project uses a wide variety of sources when collecting information for the database. The one common criterion is that the sources are published and available to the general public.

> [...]

> The type of open information used by SIPRI cannot provide a comprehensive picture of world arms transfers. Published reports often provide only partial information, and substantial disagreement among reports is common.

According to a U.S. Senate report over $1 billion dollars' worth of weapons' components, including nuclear, chemical, biological and missile technology have been sold by US companies to Saddam.

>Consider the Iraqis who did the actual door-to-door surveying. Do you think that they appreciated having such a well paying job? Do you think that they hoped for more such work? If you were them, would you be tempted to shade the results just a little so that the person paying you was happy?

This is orientalist nonsense. Yeah, David, those crafty Iraqis can't be trusted when we haven't got our eyes on 'em! Scientists from other countries don't adhere to scientific methods when they carry out their studies! Their work is always shoddy, cobbled-together bits of lies!

Fuck you, buddy.

In #6 above, David Kane wrote:

Consider the Iraqis who did the actual door-to-door surveying. Do you think that they appreciated having such a well paying job? Do you think that they hoped for more such work? If you were them, would you be tempted to shade the results just a little so that the person paying you was happy?

In context, this seems as true now as it was then. In fact, it was even prescient! The interviewers gave Roberts et al what Roberts expected to find and, sure enough, Roberts hired them again two years later.

Ah. I had overlooked this when [David Kane](http://www.apa.org/journals/features/psp7761121.pdf) first wrote it. Um, David? I wouldn't be crowing too much about prescience. The data collectors weren't paid for either study--they volunteered their time. Let's see: in 2005 you claimed that they skewed the results because they were paid. Now you gonna claim that they skewed the results because they volunteered?

Robert,

Do you have a cite for the claim that "The data collectors weren't paid for either study--they volunteered their time." I don't have a cite for the claim that they were paid, but that was my understanding, perhaps mistaken.

And did you have any interest in the bet/prize above? I think that SG is right and that you can't replicate the confidence intervals for the relative risk and excess deaths estimates. Prove me wrong and I'll donate $100 to you or to a charity of your choice.

By David Kane (not verified) on 17 Sep 2007 #permalink

According to a U.S. Senate report over $1 billion dollars' worth of weapons' components, including nuclear, chemical, biological and missile technology have been sold by US companies to Saddam.

Actually, I don't see any such thing in the article you link to. On the first page it says we sold "components needed to build nuclear weapons and diverse types of missiles." But if you read on, these "components" turn out to be computers used to design missiles, not actual components that were part of the weapons.

Yes, we sold Iraq "dual use" technology such as computers, that potentially had military applications. Meanwhile, the French and the Russians were selling actual military equipment: fighter planes, tanks, air-defense systems and so on. So while we were selling Iraq computers that may have been used to design missiles, the French were selling missiles. Not to mention uranium and a "research" nuclear reactor for enriching the uranium.

Though the article doesn't mention it, the US had an arms embargo on Iraq, and never sold Saddam any arms, not one single bullet. Instead, the article tries to hype things like the sale of US trucks to Iraq, trucks that might have been used by the Iraqi army!

Similarly, the article tells us ominously that a US firm "was building an ethylene facility. Ethylene is a necessary ingredient for thiodiglycol [a precursor to mustard gas]." Indeed this is true. The article doesn't mention that Ethylene is also used to make polyethylene, the world's most widely used plastic. According to Wikipedia, "Ethylene is the most produced organic compound in the world; global production of ethylene exceeded 75 million metric tons per year in 2005."

The article is titled, "anthrax for export," and points out that we sold anthrax spores to Iraqi scientists. What it doesn't mention is that anthrax is disease common in sheep and cows. So we were hardly in a position to prevent Iraq from obtaining anthrax: Iraq has lots of sheep. Similarly, the article decries our sale of e. coli to Iraq, not mentioning that e. coli is a gut bacteria found in many mammals. Human feces is teeming with e. coli! If Rumsfeld took a shit in Iraq, he might have provided Saddam with trillions of e. coli bacteria! Sounds like a war crime to me!

Ragout:

You apologetics are ridiculous. I guess the Iraqis grew tired of the anthrax from their sheep, so they asked the U.S. for some more, and the U.S., out of politeness, presumably, obliged.

> "It was later learned that these microorganisms exported by the United States were identical to those the United Nations inspectors found and removed from the Iraqi biological warfare program."

> [...]

> The exports continued to at least November 28, 1989, despite evidence that Iraq was engaging in chemical and biological warfare against Iranians and Kurds since as early as 1984.

Sortition,

Various strains of Anthrax and all kinds of diseases were available from scientific supply companies. Iraqi scientists bought some just like any other scientist in the world could. This stuff isn't top secret.

If you're suggesting that the US government supported Iraqi biological weapons research, that's ridiculous. And I note that you aren't able to defend the rest of your claim that the US sold "weapons' components, including nuclear, chemical, biological and missile technology have been sold by US companies to Saddam."

I just noticed that you claim that Saddam used biological weapons against the Kurds. Evidence? By evidence, I mean something better than an unsourced claim from a journalist who thinks that ethylene is some kind of dangerous chemical weapon.

David Kane, advancing: Consider the Iraqis who did the actual door-to-door surveying. Do you think that they appreciated having such a well paying job?

David Kane, retreating: I don't have a cite for the claim that they were paid, but that was my understanding, perhaps mistaken.

David,

It would be interesting to know how you got this "perhaps mistaken" impression. Also, and bearing in mind that Baghdad physicians haven't been short of work in recent years, what's your idea of a good rate of pay for the job? (Note that you believed not only that they were paid by the JHU team, but that they were rather well paid.)

Since you think $100 should be enough to persuade a professor of demography to do your homework for you, I strongly suspect that your notions of appropriate remuneration for Iraqi doctors may be a bit on the mean side. Of course that's only my impression, perhaps mistaken.

The fact that you are still looking for someone who can compute a CI for you suggests that you need to revise your bid.

By Kevin Donoghue (not verified) on 17 Sep 2007 #permalink

David:

Most of my teaching responsibilities fall between about Monday afternoon and Thursday afternoon, leaving Friday to Monday morning for my own research. I don't ordinarily recount the dull minutiae of my life but in this case I thought I'd explain that if my responses from Monday through Thursday appear to be short or delayed, it's because of the demands of my schedule and not because I've suddenly started thinking "hey, that [David Kane](http://www.google.com/url?sa=t&ct=res&cd=1&url=http%3A%2F%2Fwww.apa.org…) guy sure is making sense."

Meanwhile, what Kevin said. Also, one more piece of information: Roberts has said that the total budget for the 2004 study was (well?) under $50,000. After expenses, maybe they got a little Cross pen and pencil set or a small-sized T-shirt that said, "My dad visited 33 clusters all over Iraq and all I got was this lousy T-shirt."

Ragout:

Again, your apologetics are pathetic.

Maybe the Soviet tanks were being used as gigantic paper weights rather than as weapons.

Kevin,

It is completely standard to pay interviewers. I can't come up with an example of a survey in which the interviewers (unless they are also authors on the paper itself) were not paid. Of course they were paid (with the possible exception of the Iraqi author).

In inviting Robert to provide a cite and allowing the possibility that I might be wrong, I was being polite. They were paid. You think that they would take weeks of time away from their real jobs to do this for free?

By David Kane (not verified) on 18 Sep 2007 #permalink

David,

Re data collection: "Over three weeks, six trained Iraqi volunteers surveyed 7,868 people in 33 locations throughout the country." (http://www.jhu.edu/jhumag/0207web/number.html).

The fact that they are described as volunteers does not necessarily mean that they were not paid; after all, the Americans in Iraq are part of an "all-volunteer" army. Nonetheless, since you claim that the results were influenced by the fact that these volunteers were so "well-paid," it is your responsibility to provide evidence to indicate that profit was indeed their motive. To do this plausibly, you need to demonstrate that their participation in the survey resulted in greater profit than they would gain from alternative employment.

Can you tell us how much money they made, David? Given that five of the six were medical doctors, can you provide some income statistics for Iraqi doctors, so that we have some numbers for the sake of comparison?

Bruce

Another example of David Kane's favourite mode of reasoning: "I can't come up with an example of a survey in which the interviewers (unless they are also authors on the paper itself) were not paid." From which it evidently follows that nobody has ever done a survey pro bono. Is there a name for this particular fallacy?

As Bishop Berkeley might point out, it is possible that God has knowledge of such a study and hence it continues to exist even when David Kane falls asleep.

"You think that they would take weeks of time away from their real jobs to do this for free?"

Keep moving them goalposts David, it's great exercise for you. No, it is not my contention that the Iraqi doctors took unpaid leave "from their real jobs" in order to do the survey. Probably they saw it as part of their job as doctors and their employers saw it that way too, so they continued to get paid while they did it. If, as you evidently suppose, they got a fat bonus for doing the work your argument would make sense but - not for the first time - you are prodigal with assertions and miserly with evidence.

By Kevin Donoghue (not verified) on 18 Sep 2007 #permalink

If you have any doubts as to what the $50,000 was used for, e-mail the authors and ask them! I prefer to only bother them with substantive questions.

By David Kane (not verified) on 18 Sep 2007 #permalink

kane has got you guys arguing about the wrong thing.

David Kane has made the implication - not an outright charge, but clearly stated as a possibility - that the people doing the polling reported the answers they got because they were paid and these were the answers that were wanted.

Kane is not quite saying - but clearly putting in the middle of the conversation - that the authors bought the result they wanted, either by design or through some kind of negligence.

It is a scurrilous and despicable tactic that Kane is using here. And all of you, by arguing the wrong point - whether they were paid (who cares!)- you all are letting the vile implication that Kane made continue to stand. Not only continue to stand, but continue to sit there implicitly in the middle of the conversation. The serious issue is not whether they were paid, but kane's implication that they returned false results to further personal interest.

kane, you charged by strong implication that the field people returned the results that the Lancet authors desired from them, not the results that they actually got, out of pecuniary interest. Indeed, you implied that they got hired a second time because they did so the first time, so that the author's rewarded them for false information. That is a very serious charge - indeed, it essentially constitutes a charge of academic misconduct. Is that really the charge you want to make? If so, do you have ANY evidence for this charge, other than that it is something you imagine might happen sometimes? Will you share that evidence - and if not, will you dissociate yourself from that despicable unsupported implication of dishonesty?

Lee-
After following this for some time, there's one conclusion I've arrived at: David doesn't do evidence. Empty accusations are his mètier.

David says: "If you have any doubts as to what the $50,000 was used for, e-mail the authors and ask them! I prefer to only bother them with substantive questions."

...from which we can infer that David himself concedes that his accusation lacks substance.

Sortition,

You continue to misconstrue my rather obvious claims, which are as follows. (1) the Soviet Union and France were selling Iraq all the weapons Saddam wanted, so there was little point in extending the US arms embargo to include widely-available "dual-use" goods such as ethylene, trucks, or even computers and anthrax. (2) The article you cite isn't reliable because it makes numerous completely absurd claims.

I'm pressing this because your claim that the US sold weapons to Saddam is both common and ridiculous. I've always wondered how anyone could possibly believe them.

I'm pressing this because your claim that the US sold weapons to Saddam is both common and ridiculous. I've always wondered how anyone could possibly believe them.

apart from giving money, they gave satellite data to target Iran. and they stopped a UN resolution on iraqi use of chemical weapons. hard facts, undeniable.
http://www.parstimes.com/news/archive/2003/arming_iraq.html

do not believe everything that your government tells you.
just look at how Petraeus contradicted the numbers in the latest pentagon quaterly report:
http://www.democracyarsenal.org/2007/09/fuzzy-numbers-a.html

> I'm pressing this because your claim that the US sold weapons to Saddam is both common and ridiculous.

No. You are finding excuses for the established facts because you find them inconvenient. Your incredulity at the idea that the US could have armed Saddam shows your personal bias and nothing else - the US has a long record of arming dictators, as long as they are friendly dictators. Saddam attacking Iran made him an ally and thus a natural recipient of US support.

As for your specific points: The only one of your points that has any merit to it is the one about the possible use of ethylene for plastics. Even that point is weak when dealing with a country with an established record of using chemical weapons.

Your other points are just silly excuses. There could theoretically be non-military uses for anything - as I wrote, a tank could be used as a paper weight.

You are just employing the partisan method of picking over every fine detail of set of facts when they are inconvenient, and raising the bar of evidence to absurd levels. Convenient assertions, on the other hand, are accepted at face value even when no evidence is provided.

I was going to write something about numbers. I was going to write something about stories refugees told me fifteen years ago. I was going to write something about what is and is not important. Anything I could say, however, has been said more eloquently, too many times to count. Here, for example:

http://riverbendblog.blogspot.com/

Bring your very best math, all. Bring your best math, and make it all vanish. Throw it into the bit bucket of a null hypothesis that has just barely been rejected. Push it into the yawning chasm of a confidence interval that is just too wide.

Turn it off. Turn it off, it'll go away...