> We were recently asked by an anonymous reviewer to
> include a power analysis on a manuscript submitted to
> a prominent medical journal. I always understood that
> such power analyses were not recommended (i.e. you
> should not do them) but I am not sure why. Can anyone
> please cast some light on this issue?
>
Here are a couple of references on this topic...
Goodman SN, Berlin JA (1994) The use of predicted confidence intervals when
planning experiments and the misuse of power when interpreting results. Annals of
Internal Medicine 121:200-206
(You may be able to view this online at http://www.annals.org/cgi/content/full/121/3/200)
Hoenig JM, Heisey DM (2002) The Abuse of Power: The pervasive fallacy of power
calculations for data analysis. The American Statistician 55:19-24
HTH's
Neil
Neil Shephard
Genetics Statistician
ARC Epidemiology Unit, University of Manchester
[email protected]
[email protected]
"If your result needs a statistician then you should design a better experiment" -
Ernest Rutherford
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
