You'll have heard the news about this.
The Lancet has published a follow-up study by the
same team that did the 2004 cluster-sample study.
Their article, and the Lancet editorial comment,
can both be freely downloaded from the Lancet website:
Article:
http://www.thelancet.com/webfiles/images/journals/
lancet/s0140673606694919.pdf
[all one line]
Comment:
http://www.thelancet.com/webfiles/images/journals/
lancet/s0140673606694920.pdf
[all one line]
Politicians have, not unexpectedly, been dismissing
this study as "not credible" and "flawed". I'm struck
by the repeated use of "extrapolated": this strikes me
as yet another play on words, confusing generalisation
from sample to population -- which is well-founded and
has its well-established mechanism for reporting the
uncertainties involved -- with true extrapolation,
which is the application of results derived from data
obtained in one set of circumstances, to a quite
different set of circumstances which were not in the
original sampling frame (and which, therefore, had no
chance of contributing to the original sample).
As previously, the researchers seem to have taken pains
to point out possible sources of bias, etc.; and nowhere
does it seems that extrapolation (in the proper sense
of the words) has been done.
The political reactions, broadcast repeatedly by the
media, risk planting the seeds of distrust in the public
mind towards all things statistical!
Best wishes to all,
Ted.
--------------------------------------------------------------------
E-Mail: (Ted Harding) <[log in to unmask]>
Fax-to-email: +44 (0)870 094 0861
Date: 12-Oct-06 Time: 10:32:14
------------------------------ XFMail ------------------------------
******************************************************
Please note that if you press the 'Reply' button your
message will go only to the sender of this message.
If you want to reply to the whole list, use your mailer's
'Reply-to-All' button to send your message automatically
to [log in to unmask]
Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk.
*******************************************************
|