### 100,000 Dead—or 8,000 in Iraq?

In Slate of all places

How many Iraqi civilians have died as a result of the war?

The authors of a peer-reviewed study, conducted by a survey team from Johns Hopkins University, claim that about 100,000 Iraqi civilians have died as a result of the war. Yet a close look at the actual study, published online today by the British medical journal the Lancet, reveals that this number is so loose as to be meaningless.

The report's authors derive this figure by estimating how many Iraqis died in a 14-month period before the U.S. invasion, conducting surveys on how many died in a similar period after the invasion began (more on those surveys later), and subtracting the difference. That difference—the number of "extra" deaths in the post-invasion period—signifies the war's toll. That number is 98,000. But read the passage that cites the calculation more fully:

We estimate there were 98,000 extra deaths (95% CI 8000-194 000) during the post-war period.

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.

The standard issue line in the blogosphere is "read the whole thing" but save yourself the pain. The author summed it up, "This isn't an estimate. It's a dart board."

I'm sure I'll draw fire for this line, but I bet I could get a paper peer reviewed today that said the earth was flat. -- As long and I put in the right ideological dogma.

Thank you, Paul. You know, ... (Below threshold)
Jim:

Thank you, Paul. You know, when I read an AP story about this poll -- the story zeroed-in on 100,000 Iraqis killed -- the first thing I wondered was: What methodology was used to establish that number? I also wondered who these reviewers were and what their agenda is for doing the study (as if I don't already know -- it's meant to embarass the United State military).

Also, no where in the AP article did it differentiate between combatants and innocent civilians. Also, there appears to have been no effort to discover whom was responsible for the deaths.

A range of 8,000 to 194,000 is quite a stretch for a supposed scientific study.

I think this is propaganda disguised as science. But then I'm suspect of most of academia's studies.

Shortly after our liberatio... (Below threshold)
jake:

Shortly after our liberation, the Iraqi government found a list of Iraqis who were scheduled to die at the hands of Saddam’s butchers in the next 12 months.

That list contained 77,000 names.

The media, academia, big bu... (Below threshold)

The media, academia, big business, politicians -- you can't believe any of them.

That's why I now believe only people who agree with me, since I'm always right. ;-)

8,000 to 194,000... push th... (Below threshold)
Russ:

8,000 to 194,000... push the boundaries of the statistical method on that and you could end up with zero deaths.

Push farther and you could end up with -2,000 deaths.

So... what was that old line about lies, damned lies, and statistics?

Oh.my.god - this takes the ... (Below threshold)
BR:

Oh.my.god - this takes the cake!
And does this include those dying of old age and due to longterm malnutrition from Saddam/UN/et al's diversion of funds from the Food for Oil program? Pogrom?

Paul, if you haven't you mu... (Below threshold)

Paul, if you haven't you must read about the Sokal Hoax where a scientist stuffed a bunch of postmodern junk into a paper and got it published. Only then did he come out and proclaim that it was all made up.

http://skepdic.com/sokal.html

An astronomical 95% confide... (Below threshold)
Mike:

An astronomical 95% confidence interval like this means that the standard deviation for their data was huge. That is usually a tell-tale indication of two things (both bad):

1) Your data values are scattered all over the place and do not trend toward a mean value

or

2) You have an insufficient amount of data to draw a defensible conclusion

In either case, a respectable researcher would throw away his data and start over.

It is upsetting that an institution such as Johns Hopkins could publish a study that was so obviously based on poor data and then try to pawn it off as "news". Shame on them, and on the poor suckers that were conned by this worthless effort.

Since most of us (if not al... (Below threshold)
-S-:

Since most of us (if not all) are focused on the reality that is the preponderance of irrational claims recently as "news" -- from both academia, so to speak, and journalism, which they say but few believe lately -- I think it shows to what extent these two very encompassing areas are influenced by those who pay their bills, including salaries.

After all, any source is only as accurate as is the department head and dean, and/or the editor and publisher, respectively. And they have to respond to donors and investors. Such that, a few people with billions of dollars to devote to philanthropy...make a difference in what shows up in the classroom, on the page, on the air.

Shocking, but that's the reality of the way our world is recently. Strange that it's those who work hard to overthrow capitalism and free markets who are most responsible for this sort of opinion casting, results editing by influence...errr, requirement.

Ok, I'm going out on a limb... (Below threshold)
Gekkobear:

Ok, I'm going out on a limb here, but I'm going to state that the number of deaths is definitely 99% within the range of 0 and 25,374,691 (estimated population from http://www.wordiq.com/definition/Iraq for July 2004).

Using the same "statistical variance" I guess we'll estimate 12.5 million dead (as we don't know anything, but its right between my two numbers)?

So from my living room, with no supporting evidence, I can clearly (statistically) state that there were 12.5 million deaths in Iraq (99% CI 0 - 25,375,691) TODAY ALONE. Is anyone supposed to be impressed? Are I a rocket surgeon yet?

I'm outraged that a once-re... (Below threshold)

I'm outraged that a once-respectable journal like The Lancet can fast-track this to print just to try for a cheap political hit at election time.

It makes me wish I was a doctor just so I could drop my subscription. How can we trust anything they print now?

Here's a page full of contacts for The Lancet, including their US offices:

http://www.thelancet.com/contact

FDR...led us into World War... (Below threshold)

FDR...led us into World War II.

Germany never attacked us: Japan did. From 1941-1945, 450,000 lives were lost an average of 112,500 per year.

Truman...finished that war and started one in Korea. North Korea never attacked us. From 1950-1953, 55,000 lives were lost an average of 18,334 per year.

John F. Kennedy...Started the Vietnam conflict in 1962. Vietnam never attacked us.

Johnson...turned Vietnam into a quagmire. From 1965-1975, 58,000 lives were lost an average of 5,800 per year.

Clinton...went to war in Bosnia without UN or French consent, Bosnia never attacked us. He was offered Osama bin Laden's head on a platter three times by Sudan and did nothing. Osama has attacked us on multiple occasions.

In the two years since terrorists attacked us, President Bush has....liberated two countries, crushed the Taliban, crippled al-Qaeda, put nuclear inspectors in Libya, Iran and North Korea without firing a shot, and captured a terrorist who slaughtered 300,000 of his own people.

The Democrats are complaining about how long the war is taking, but...It took less time to take Iraq than it took Janet Reno to take the Branch Davidian compound. That was a 51-day operation.

We've been looking for evidence of chemical weapons in Iraq for less time than it took Hillary Clinton to find the Rose Law Firm billing records.

It took less time for the 3rd Infantry Division and the Marines to destroy the Medina Republican Guard than it took Ted Kennedy to call the police after his Oldsmobile sank at Chappaquiddick.

It took less time to take Iraq than it took to count the votes in Florida!!!!

http://www.baptistboard.com/cgi-bin/ultimatebb.cgi/topic/18/2382.html?

## Contact

Send e-mail tips to us:

[email protected]

## Credits

Section Editor: Maggie Whitton

Editors: Jay Tea, Lorie Byrd, Kim Priestap, DJ Drummond, Michael Laprarie, Baron Von Ottomatic, Shawn Mallow, Rick, Dan Karipides, Michael Avitablile, Charlie Quidnunc, Steve Schippert

Emeritus: Paul, Mary Katherine Ham, Jim Addison, Alexander K. McClure, Cassy Fiano, Bill Jempty, John Stansbury, Rob Port

In Memorium: HughS

Hosting by ServInt

Ratings on this site are powered by the Ajax Ratings Pro plugin for Movable Type.

Search on this site is powered by the FastSearch plugin for Movable Type.