Radford Neal wrote:
> Yes indeed. And the context in this case is the question of whether
> or not the difference in performance provides an alternative
> explanation for why the men were paid more (one supposes, no actual
> salary data has been released).
I disagree. The original context was that. The baseball example was in
relation a more general question, else why was it introduced?. (The thread
header changed, for example).
If you want to say there is a difference. Fine. No dispute.
If you wish to infer that difference is "huge" that requires more than an
observation of a difference - you need to explain and support that inference
in some way. My point was that the baseball case allows you to state a
difference, but an inference about the size of the difference requires further
support. In the baseball case that support comes almost entirely from
knowledge of baseball. (Was I really _that_ unclear?).
> In this context, all that matters is that there is a difference. As
> explained in many previous posts by myself and others, it is NOT
> appropriate in this context to do a significance test, and ignore the
> difference if you can't reject the null hypothesis of no difference in
> the populations from which these people were drawn (whatever one might
> think those populations are).
Only if the the entire content of the claim is that 1) there is a difference,
2) that difference might possibly explain something else.
Once you extend the claim to say there is, for example, a "huge" effect. Also
if you entertain other hypotheses (or allow others to) the situation might change.
Thom
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
