100,000 Iraqi Civilians have died in current war

[Schrodinger's Cat]

Originally Posted by russotto

To reiterate what UT said earlier, the actual figure, taking into account only sampling error, was 101,000 plus or minus 93,000. When your error bars are of the same magnitude as your data points, you don't have data; you have junk.

You don't understand statistical sampling. Here's a rough graph of what the results show. The probability (0 - 1) of any given number being the correct one is a point on the y-axis, the number of casualties (1 - 300,000) is a point on the x-axis. When graphed, you get the following bell shaped curve (sorry it ain't prettier, but I've got work to do):

[Happy Monkey]

Shouldn't that 300,000 be 200,000?

[Schrodinger's Cat]

Originally Posted by Happy Monkey

Shouldn't that 300,000 be 200,000?

yeah, I just threw it in there as the extreme with 0 probability. like I said it's a quick and dirty just to give people a basic understanding of how the numbers work.

[russotto]

I _do_ understand statistical sampling. They didn't give the confidence interval for that range, unfortunately. But I think you've drawn your curve with too small a std deviation.

And remember that's considering only statistical sampling uncertainty.

[Schrodinger's Cat]

Originally Posted by russotto

I _do_ understand statistical sampling. They didn't give the confidence interval for that range, unfortunately. But I think you've drawn your curve with too small a std deviation.

And remember that's considering only statistical sampling uncertainty.

Hey, what do you want from a sketch drawn on a Domino's pizza napkin while at the same time going over notes for my next lecture? Next time I'll send it in for peer review, first. Good to know someone else around here understands sexually transmitted diseases among deviates!

Seriously, anyone who questions the sampling methodology or linear regression techniques used should at least take a look at the original paper published in The Lancet. http://www.thelancet.com/home
Registration is free and the document can be found here:
http://pdf.thelancet.com/pdfdownload...1264.1&x=x.pdf

The conclusions this study draws have grave implications regarding the US conduct of the war. Dismissing the data without even looking at the source is not what I would have expected from educated people who honestly want to understand what is happening in Iraq.

[Undertoad]

So is accepting the data. It's bullshit on its face, and you want to believe it so hard.

All it takes is a little numeracy and a functioning bullshit detector, not a degree in statistical analysis.

At one point they claim to have seen death certs for a majority of the dead. If there are certs, the information has been documented and can be confirmed. Where are the hospitals with this information? How do they have time to process the injured and dead to the point where they can document them? This is a similar number of dead in an area much smaller than the area affected by the tsunami. Hussein required mass graves to bury a similar number over many years. Where are the graves? Where are the fuckin' wounded? Where are the fuckin' bodies already???

"On the 25th of September my focus was about how to get out of the country," he recalls. "My second focus was to get this information out before the U.S. election."

I wonder why the pundits say it was political?

May I add, "DUH" ?

[Happy Monkey]

Originally Posted by Undertoad

I wonder why the pundits say it was political?

May I add, "DUH" ?

If it were true, wouldn't it be best if it were revealed before the election? That's hardly indicative of anything.

[xoxoxoBruce]

They decided where to take the samples and couldn't so they took them where they decided they shouldn't.
Take a national poll of who will win the Supe...Big Game but you can't do in nationally, so do it just in Philly. Yeah that will be accurate.

[Schrodinger's Cat]

Originally Posted by Undertoad

So is accepting the data. It's bullshit on its face, and you want to believe it so hard.

All it takes is a little numeracy and a functioning bullshit detector, not a degree in statistical analysis.

At one point they claim to have seen death certs for a majority of the dead. If there are certs, the information has been documented and can be confirmed. Where are the hospitals with this information? How do they have time to process the injured and dead to the point where they can document them? This is a similar number of dead in an area much smaller than the area affected by the tsunami. Hussein required mass graves to bury a similar number over many years. Where are the graves? Where are the fuckin' wounded? Where are the fuckin' bodies already???

"On the 25th of September my focus was about how to get out of the country," he recalls. "My second focus was to get this information out before the U.S. election."

I wonder why the pundits say it was political?

May I add, "DUH" ?

You may indeed add "DUH." Only about 1/3 of Iraqi war related deaths occur in hospitals. When checking data from funeral homes or morgues the problem is that these entities do not list whether the dead were combatants or members of the civilian population. Your questions about the reliability of both hospital records and about what the Iraqi government might say about the percentage of death certificates that were for innocent civilians are valid points. This is why the researchers used the technique of having Iraqi surveyers go door to door and ask detailed questions of the respondents. This study was scrupulous in its evaluation techniques to seperate out combatant versus civilian dead.

A major concern has also been whether there has been a rise in infant mortality rates pre and post Saddam's rule and the advent of the war. Many women no longer go to hospitals to give birth due to security reasons and the researchers wished to see what, if any, impact this has had on infant death rates.

Finally, why do you assume that voters of whatever political persuasion would have no interest in a valid estimate of Iraqi civilians killed in the war? Perhaps you are concerned that the researchers' conveying the information that US soldiers who had accidently killed civilians actually went to the families of the deceased and apologized, would have swung voters to the Republican side? Good thing this was not widely reported and Kerry got elected after all.

[Undertoad]

The quote doesn't indicate that it wouldn't swing the election. The quote indicates that the researcher's interest was blatantly political, which in turn suggests a political bias to the study.

If I had become convinced that a hidden massacre was going on, my second concern would be notifying the UN or world press in an attempt to stop it. Swaying an election in which both participants had a nearly identical policy to how to further manage Iraq? Low on my priority list.

100,000 in a country of 24,000,000 is 1 in 240. Who would kill that many, and how? Indiscriminate bombing has definitely happened -- mistakes were made -- just not THAT many.

That number of deaths would have been noticed before this guy made his excursion. Iraq is a violent place, sure, but is functioning as a society to the point where it can notice such things. Even the insurgency is sophisticated enough to notice and promote such things. They feed their own media, and once in a while ours, with their own propaganda. Civilian tragedy makes every news feed in the world. It would have been noticed.

And by the way, who risks their life to that level to bring back statistics? Doesn't the bare fact that he made the trip make you suspicious of his numbers?

And hey, on that point... isn't it ironic that his cover was blown multiple times as this blue-eyed westerner goes around collecting information, through what is apparently an unheard-of level of violence, and yet -- through the chaos of 1 in 240 killed -- he makes it out of the country somehow unscathed without protection from anyone but his translators? The mere fact that his head is not separate from his body is evidence contrary to his so-called "findings".

[Happy Monkey]

Originally Posted by Undertoad

If I had become convinced that a hidden massacre was going on, my second concern would be notifying the UN or world press in an attempt to stop it. Swaying an election in which both participants had a nearly identical policy to how to further manage Iraq?

...But only one of whom was directly responsible for the current situation.

[Schrodinger's Cat]

Originally Posted by Undertoad

The quote doesn't indicate that it wouldn't swing the election. The quote indicates that the researcher's interest was blatantly political, which in turn suggests a political bias to the study.

If I had become convinced that a hidden massacre was going on, my second concern would be notifying the UN or world press in an attempt to stop it. Swaying an election in which both participants had a nearly identical policy to how to further manage Iraq? Low on my priority list.

The researchers never call these fatalities a "hidden massacre." That is your label, and, interestingly enough, your perception of the study results. The publication of the research findings in the highly prestigous British medical journal, Lancet, is surely one way of attempting to draw attention to the situation by the UN and the world press. Perhaps, the report was met with too many responses such as your own?

Originally Posted by Undertoad

100,000 in a country of 24,000,000 is 1 in 240. Who would kill that many, and how? Indiscriminate bombing has definitely happened -- mistakes were made -- just not THAT many.

Actually the CIA Factbook gives Iraq's 2004 population as over 25,000,000. Are you saying those civilians deaths were carried out on purpose?

Originally Posted by Undertoad

That number of deaths would have been noticed before this guy made his excursion. Iraq is a violent place, sure, but is functioning as a society to the point where it can notice such things. Even the insurgency is sophisticated enough to notice and promote such things. They feed their own media, and once in a while ours, with their own propaganda. Civilian tragedy makes every news feed in the world. It would have been noticed.

I'm sure the Iraqi's noticed it, but that was just propaganda, right? The US military refuses to do civilian body counts, so they were REFUSING to notice it. Obviously, civilian tragedy in this instance gets ignored, since the most reputable study of it in Iraq to date was pretty much ignored in the media at the time it came out. So far as I know, The Chronicle of Education is the only outfit that has pointed this omission out.

Originally Posted by Undertoad

And by the way, who risks their life to that level to bring back statistics? Doesn't the bare fact that he made the trip make you suspicious of his numbers?

This same man risked his life tallying the dead in the civil conflict in Rwanda where his estimates were widely accepted by the UN and the rest of the world. He is an expert in his field. Geologists and seismologists risk their lives and have even been killed studying volcanic activity. No one questions their research, as a result, however.

Originally Posted by Undertoad

And hey, on that point... isn't it ironic that his cover was blown multiple times as this blue-eyed westerner goes around collecting information, through what is apparently an unheard-of level of violence, and yet -- through the chaos of 1 in 240 killed -- he makes it out of the country somehow unscathed without protection from anyone but his translators? The mere fact that his head is not separate from his body is evidence contrary to his so-called "findings".

I'm not sure where you get your "multiple times." He kept an extremely low profile and hired Iraqi citizens to do the actual surveys. Perhaps his survival has something to do with his authenticity as a world renowned social scientist?

[Undertoad]

Originally Posted by Schrodinger's Cat

The researchers never call these fatalities a "hidden massacre." That is your label, and, interestingly enough, your perception of the study results. The publication of the research findings in the highly prestigous British medical journal, Lancet, is surely one way of attempting to draw attention to the situation by the UN and the world press. Perhaps, the report was met with too many responses such as your own?

It would be a hidden massacre. The percentage population gone would be hundreds of times higher to Iraq than 9/11 was to the US.

They are claiming 183 deaths per day. Assuming a 2:1 injury to death ratio that's 549 people dead or injured per day! And we haven't even mentioned yet that half the country was basically at peace so the killing would have to be kind of concentrated, and impossible not to notice.

In Fallujah we went into full out urban warfare and killed about 800 in a couple of days. The entire resistance is estimated at about 15000.

Are you saying those civilians deaths were carried out on purpose?

Why would we kill that number of people? Bad aim?

Here is the Slate article that helps to debunk this crapola

[Undertoad]

Oh yeah, another reason it was ignored: people, and especially the media, seem to have realized that news items released 2-3 days before the election have a high probability of being bogus because everyone in the world has an interest in swaying the election.

If the Lancet really wanted to do a job of it, they should have published two weeks out. That way even if the numbers are crap, the issue gets water cooler time and some people will believe it and push the election on that basis.

[russotto]

OK, now I've looked at the study. That range is the double-ended 95% confidence interval (excluding Fallujah). That's not so great. Then you get into the problems with methodology, which UT has outlined quite well.

Furthermore, I see no claim in the study that these were civilian deaths. That appears to be someone else's addition.

The study is junk.