Stan Brown wrote:
>
> Jerry Dallal <[EMAIL PROTECTED]> wrote in sci.stat.edu:
> >VOLTOLINI wrote:
> >>
> >> What is a P value? Does anyone can give a simple explanation? I am not
> >
> >A P value is the smallest fixed level for which the test statistic
> >would lead to rejection of the null hypothesis. For example, if P =
> >0.023, then anyone who tested the corresponding null hypothesis at a
> >fixed level greater than 0.023 (e.g., 0.05) would reject, while
> >anyone working at a fixed level less than or equal to 0.023 (e.g.
> >0.01) would fail to reject.
>
> Maybe I'm not understanding you, but that sounds like a tautology
> and not a definition. We preselect an alpha, and then we reject the
> null hypothesis if p < alpha. To say that p is the smallest level
> for which you would reject is just to say that you reject if p <
> alpha.
>
> Am I missing something in your explanation?
Maybe. It's not tautological. P - min{alpha such that hypothesis is
rejected). I make the point on my web page that P values make sense
only in the context of fixed level testing. Otherwise, you leave
yourself open to Harold Jeffrey's criticism that those who do
hypothesis testing act on the basis of rare events that they don't
see. If one says only that the P value is the probability of seeing
results as or more extreme than what was observed, one leaves one's
self open to the question, "Why should I care about the probability
results I haven't seen?"
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
