On Mon, Jun 16, 2008 at 4:31 PM, Allan Reese (Cefas)
<[log in to unmask]> wrote:
> In addition to suggestions for references reported to the list earlier, here is a more > discursive reply, and the only reply giving a reference that explicitly recommends > stars:
[snip]
I do wish journal editors would require publishing either (a) all the
relevant data used, and/or (b) estimates of the PDFs of the data.
After all, without seeing the data itself, I can't sanity check the
distributional assumptions behind the tests used to calculate
p-values, with or without stars! I suppose this also touches on the
great "effect size" debate.
Max
--
Dr Max Little (www.robots.ox.ac.uk/~littlem)
Systems Analysis, Modelling and Prediction Group (www.eng.ox.ac.uk/samp)
Department of Engineering Science
University of Oxford, Parks Road
Oxford OX1 3PJ
[log in to unmask]
Tel: 01865 311363
Mob: 07807 950801
|