>> Vassili P. Leonov wrote:
>> >"I have collected large collection of examples of misuse of statistics
> >in the dissertations and articles. Their analysis shows, that most of
> >all errors in use of statistics is observed in medicine and biology.
> >Especially it is bad when it is observed in medical work.
> > .....
>> There is no doubt that this is a very serious problem, certainly in
> biology (I can't speak for medicine), and it is not confined to Russia.
> So I would say that it is *not* solved in USA, UK ...
>> You can find examples of misuse and misunderstanding of statistics at
> all levels, in journals from the most famous to the most obscure.
>> I am pessimistic enough to doubt whether any solution is in sight, ...
I have been aware of the misuse of statistical methods
in medical research (bothh USA and UK) since starting
my doctoral work around 1980. A key article which tries
to address this is:
Altman, D G (1980) Statistics and Ethics in Medical Research,
British Medical Journal, vol 281 pp 1182-1184.
This is the first of a series in which he persues the notion
that poor statistical work is unethcal and looks at their
use. The subsequent parts are:
vol 281: p1267-9, p1336-8, p1399-401, p1473-5, p1542-4, p1612-4
vol 282: p44-47 plus letters p480 and p990
There is a strong ethos in medical publishing which suggests
that meaningfull research can only be done through controlled
trials with quantitative statistical otcomes. This notion that
statistics are good (or do I mean God?) is very pervasive
and ignores other research methods. With this sort of
preasure both authors and referees demand statistical results
even where there use is inappropriate and misleading.
Dr A D Elliman, BTech MBCS CEng Email: Tony.Elliman at brunel.ac.uk
Senior Lecturer ellimana at acm.org
& Undergraduate Course Director
Room SJ027 St Johns Building Phone: +44 1895 274000 ext 2129
Department of Computer Science or: +44 1895 203394
and Information Systems Fax: +44 1895 251686
Kingston Lane Home: +44 1923 261805
UXBRIDGE, UB8 3PH Fax: +44 1923 443548