On 23 Apr, 15:48, Mike Clark wrote:
In message
* * * * * Toom Tabard wrote:

[snip]







Not necessarily. You may not have the statistical proof, but the
empirical experience and knowledge of the practitioners in the
particular area can be strongly indicative of the true effect and
point to the flaws, and the reasons for them, in the statistical
analysis. When reality seems at variance with the numbers, it is
frequently the numbers which are flawed. There a legions of social,
health and safety studies where concentration on the numbers followng
the issues receiving concentrated attention, result in problems with
comparison with earlier data which wasn't collected under the same
spotlight, but where the empirical experience of practitioners not
involved in the statistical studies can give some, possibly the best,
evidence of the true effect.

Toom

Presumably you can cite some specific examples to substantiate your
generalisations above?


I certainly can, but you state you are a PhD, and a Reader, and in a
medical discipline. Doesn't a PhD still involve finding things out
for yourself. Most of the PhD students in my research lab seemed
capable of this.

You must, for many years have been tripping over copious specific
examples illustrating what I've said. Didn't you notice them?I didn't
know what I said was contentious. It certainly shouldn't be to any
competent and aware researcher.

Toom