Rich Ulrich wrote:
>
> On 20 Mar 2003 18:26:49 -0800, [EMAIL PROTECTED] (Karl L. Wuensch)
> wrote:
>
> > Were you to define p as the probability of getting data exactly as
> > discrepant with the null as those you obtained, given the null, then,
> > assuming you are dealing with a continuous variable, that probability is
> > always going to be quite small, eh? About as small as the probability of
>
> [snip]
> and
> > Why should I care about data more discrepant than what I've
> > observed? I haven't seen them. Why should they affect the way I
> > judge what I did observe? :-)
> >
>
> The above sounds has a point, but seems more than
> a little naive.
> Likelihood, the height of the curve, is not "probability"
> in the way we do define it.
Do you mean "probability density" here? (They are in
a sense equal, but in the context of "the curve" probability
density sounds more appropriate.
The problem here is surely that probability densities
are difficult to compare. A "critical density" that would be reasonable
for a N(0,1�) would be far too high for an N(0,10�).
Scaling this out is essentially dividing by the density of the mean.
And why should we care about values less discrepant than what we've
observed <grin>?
-Robert Dawson
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
