Dear Allstaters,
I hope some of you are interested in an RSS Local Group Seminar to be
held in Leeds next Monday - subject to the weather!
In fact, if the weather worsens and you are travelling far, then please
check our webpage, or phone, before travelling. Details at the end.
All Welcome!
Regards, Robert.
=====================================================================
Dr Robert G. Aykroyd,
Hon Secretary, RSS Leeds/Bradford Local Group,
Department of Statistics,
University of Leeds,
LEEDS, LS2 9JT, UK.
Monday 2nd February 2004
John Copas (University of Warwick)
Thinking about bias: why magnesium doesn't work but prisons might
A systematic review concluded that intravenous magnesium is effective
in reducing mortality from heart disease. But a later controlled trial
showed that magnesium is in fact completely ineffective. Recent data
comparing re-conviction rates after different sentences seem to support
the slogan "prison works". But can this analysis be trusted? Both are
examples of incomplete data, and of bias resulting from lack of
randomisation. We think about how big these biases might be.
The Meeting will be in LT10 Roger Stevens Building on the main campus
of the University of Leeds, starting at 4pm, with refreshments from
3:30pm on Level 9 in the School of Mathematics, University of Leeds.
RSS Leeds/Bradford Local Group
http://www.maths.leeds.ac.uk/statistics/rss/
School of Mathematics
http://www.maths.leeds.ac.uk/school/contacts/maths-map.gif
University of Leeds
http://tldynamic.leeds.ac.uk/leisure/city_centre.htm
|