[Dean's World] Dave Price: 600,000 Errors

[notify at powerblogs.com]

Posted by Dave Price:
600,000 Errors
http://www.deanesmay.com/posts/1160708956.shtml


   Glenn [1]links a couple posts that make good points about the
   [2]Lancet-published study from Johns Hopkins finding 600,000 excess
   deaths from the war in Iraq. I added some thoughts below.
   I debated the initial study, which claimed to find 100,000 excess
   deaths at that time, with [3]Tim Lambert and crew over at Deltoid
   pretty extensively. Some of the methodology was defensible, but the
   major problem with that study was that, even if we stipulated the
   methodology as totally sound, the only conclusion one could state with
   95% likelihood was that there had been at least 8,000 deaths and no
   more than 194,000, because the 95% confidence interval was 8,000 -
   194,000. Those intervals are done for a reason; it means that in 100
   populations of this size with this sample, in 95 of them we would
   expect the real number to actually fall between 8,000 and 194,000. 95%
   is considered the standard for a result that is meaningful. (You can
   see why; if you only expected your result to actually be correct half
   the time, you havenât really said much that matters.) But the interval
   isnât quite as egregious in the second study, so letâs move on to the
   other problems.
   One can also argue that in both studies the pre-war period they chose
   to compare to is not representative as it did not contain any of the
   major death toll events of the Saddam era. Since the purpose of the
   war was to remove Saddam, in large part explicitly [4]because of those
   very events, it seems fair to include them, but of course we know from
   their statements that the authors had no interest in being fair (see
   the [5]wiki).
   The major methodology problem in both studies was the reliance on
   reporting from citizens, which assumes a population [6]culturally
   prone to exaggeration and in some areas very hostile to the war effort
   is reliable in giving estimates of war dead. Hell, take a poll of
   Americans who claim to have been at Woodstock and youâll probably find
   8-16 times as many as were actually there. Death certificates are
   hardly reliable in a country where it has been widely reported that
   [7]all kinds of identity documents are being forged. And since
   American forces [8]typically compensate the victims of violence, there
   is financial incentive to exaggerate claims as well, and to have paper
   âproofâ of those claims.
   Remember, too, that the violence is primarily restricted to just three
   provinces plus Baghdad. That means this would be 600K excess deaths
   [9]out of about 10M, or 6%. We would also expect to see about 5 times
   as many who are merely seriously wounded. That means 3.6 million dead
   and wounded, out of 10 million, or more than a third.
   Are they joking? Baghdad would be a ghost town with numbers like that.
   Hospitals would be crammed full and spill into the street with
   casualties. Morgues would be stacking bodies twenty feet high in the
   midday sun. The smell alone would drive people out.
   Worst of all, perhaps, the "scientists" doing the study didn't even
   pretend to be objective, and have now twice published their results
   right before an election with the express intention of affecting the
   result. Rarely is even the worst agenda science this shameless. This
   entire episode reflects very badly on Lancet and John Hopkins.

References

   1. http://instapundit.com/archives/033191.php
   2. http://en.wikipedia.org/wiki/Lancet_study
   3. http://scienceblogs.com/deltoid/
   4. http://hnn.us/articles/1282.html
   5. http://en.wikipedia.org/wiki/Lancet_study
   6. http://www.dailypundit.com/2006/03/learning_to_think_like_an_arab.php
   7. http://www.cato-at-liberty.org/2006/07/11/fake-ids-save-lives-in-iraq/
   8. http://www.nytimes.com/2006/06/10/world/middleeast/10payments.html?ei=5088&en=14e9181d3f0ff195&ex=1307592000&partner=rssnyt&emc=rss&pagewanted=print
   9. http://www.citypopulation.de/Iraq.html