[R] acceptable p-level for scientific studies

John Maindonald john.maindonald at anu.edu.au
Thu Dec 19 01:38:05 CET 2002


Another interesting paper is:

Gigerenzer, G. 1998. We need statistical thinking, not statistical
rituals. Behavioural and Brain Sciences 21: 199-200.

It is interesting that Gigerenzer's recent, highly readable and
disturbing book :"Calculated Risks" (US: Simon & Schuster) or
"Reckoning with Risk" (UK, Allen Lane) has no reference to
p-values in the index.

Gigerenzer describes an investigation where just one AIDS
counsellor out of 20 showed any recognition that the estimate
of the probability of infection, given a positive AIDS test, would
depend on the risk group from which the person came.
The very small P[positive test | no infection] is an incomplete
part of the story.

Regrettably I suspect that the result would be much the same for
AIDS or genetics counsellors anywhere.

John Maindonald             email: john.maindonald at anu.edu.au
phone : +61 2 (6125)3473    fax  : +61 2(6125)5549
Centre for Bioinformation Science, Room 1194,
John Dedman Mathematical Sciences Building (Building 27)
Australian National University, Canberra ACT 0200.




More information about the R-help mailing list