Iraq Death Toll

Right, I have never stated that the study is invalid, only that the numbers shouldn't be quoted as superaccurate... People keep assuming that I am making a case for discounting the study entirely, I am not. I am only pointing out inaccuracies in the report. Pretending I have determined the study to be totally fraudulent would be disingenuous.
 
Damocles said:
Right, I have never stated that the study is invalid, only that the numbers shouldn't be quoted as superaccurate... People keep assuming that I am making a case for discounting the study entirely, I am not. I am only pointing out inaccuracies in the report. Pretending I have determined the study to be totally fraudulent would be disingenuous.
Click to expand...

That is true, I've not seen you claim the study invalid. And you are correct, the 'numbers' (really the average) should not be taken as super accurate. As in my previous post, the researchers only gather enough data to ensure that the possible values of the the populations don't intersect. If an MOE of HUGE does the job, then that's all they do.
 
Read the evalutions of these numbers. They are useless. More than half the samples were taken in Mosel and Bagdad and the two most peacefull providences have no samples. Lots of deaths occurred, no need to lie about the numbers. The point is this is a BS study.
 
toby said:
Read the evalutions of these numbers. They are useless. More than half the samples were taken in Mosel and Bagdad and the two most peacefull providences have no samples. Lots of deaths occurred, no need to lie about the numbers. The point is this is a BS study.
Click to expand...

How would taking samples in the most peaceful provinces have changed the outcome??? Why do you think they concentrated in the areas around Baghdad and Mosel???? What do you think they were counting????
 
If you read the methodology those peaceful provinces should have been included to make it more valid.
 
toby said:
Read the evalutions of these numbers. They are useless. More than half the samples were taken in Mosel and Bagdad and the two most peacefull providences have no samples. Lots of deaths occurred, no need to lie about the numbers. The point is this is a BS study.
Click to expand...
Not at all. If you need to count deaths, you need to go where the deaths are. It is often most effective to sample the extremes; thus, sampling in the most violent areas makes sense. In peaceful areas, the differences in counts might not be statistically significant with a similar sample size, and would require a larger sample size to get a valid result. If the study had a sufficient budget to allow a huge sample in a peaceful area (i.e., data takers less likely to be killed themselves) then I am sure the researchers would have done that rather than risk life or limb.

However, the researchers do realize that there are limitations to the conclusions that can be reached from the data taken at extremes. Any good stat study, and I am sure Hopkins does good work, is filed with caveats and acknowledgments of the limits to the conclusions.
 
Last edited:
Damocles said:
If you read the methodology those peaceful provinces should have been included to make it more valid.
Click to expand...

Damo,

Did you even read the methodology? Or are you repeating something from a blog?

They DID sample all 18 provinces in iraq, based on proportionality of population:


As a first stage of sampling, 50 clusters were selected systematically by Governorate with a population proportional to size approach, on the basis of the 2004 UNDP/Iraqi Ministry of Planning population estimates (table 1). At the second stage of sampling, the Governorate's constituent administrative units were listed by population or estimated population, and location(s) were selected randomly proportionate to population size.
 
Cypress said:
Damo,

Did you even read the methodology? Or are you repeating something from a blog?

They DID sample all 18 provinces in iraq, based on proportionality of population:


As a first stage of sampling, 50 clusters were selected systematically by Governorate with a population proportional to size approach, on the basis of the 2004 UNDP/Iraqi Ministry of Planning population estimates (table 1). At the second stage of sampling, the Governorate's constituent administrative units were listed by population or estimated population, and location(s) were selected randomly proportionate to population size.
Click to expand...

Table One in the Methodology section, shows how they proportionally sampled all 18 provinces, including the ones in the kurdish north.
 
yeah MIT, the bastion of rationality and the scientific method cannot be trusted as much as...say...Faux News.

and that right, write?
 
the fucking place is coming unglued and the neocons are still whistling and busying themselves rearranging the deck chairs on the Titanic while this stupid stupid war they started just erupts in bloodshed of mind numbing proportions.

may you all burn in hell.
 
The main point to me is that this war was a mistake and 1 death from Bush's Blunder is too many. It is not a matter of how many, but that there are any at all.
 
uscitizen said:
The main point to me is that this war was a mistake and 1 death from Bush's Blunder is too many. It is not a matter of how many, but that there are any at all.
Click to expand...
I agree, and I never did support our invasion of Iraq - not from Day One, not now.
 
Cypress said:
Damo,

Did you even read the methodology? Or are you repeating something from a blog?

They DID sample all 18 provinces in iraq, based on proportionality of population:


As a first stage of sampling, 50 clusters were selected systematically by Governorate with a population proportional to size approach, on the basis of the 2004 UNDP/Iraqi Ministry of Planning population estimates (table 1). At the second stage of sampling, the Governorate's constituent administrative units were listed by population or estimated population, and location(s) were selected randomly proportionate to population size.
Click to expand...
Yes, hence the reason I stated that those peaceful provinces should be included according to the methodology...
 
The main point of the research and the report was to suggest that the number of Iraqis killed so far in the Iraq war is roughly 655,000 or some similar/other number between 400,000 and 950,000. If you have a problem with that prove the research and the report incorrect. It is really quite simple. Prove their number wrong. Or accept it and move on.org...

If you don't like it you can always migrate to George W. Bush's new favorite oppressive country in Central & South America, Guatamala...
 
You must log in or register to reply here.
Back
Top