On Wed, 4 Apr 2001, Erik <[EMAIL PROTECTED]> wrote:
> What is the p-value of a t-statistic significant (significant level
> shown by the software is p) in the wrong direction in an one-tailed
> test? Should we modified it to (1-p)? Or it is just p?
Well, first you need to be sure it's reporting p and not 2p, as
Dennis has pointed out.
If you're reporting a result more or less formally, as in a research
report, such a result would usually be presented simply as
"(t = [value], not significant)"
(or "n.s." for "not significant").
For whatever purpose, why do you want a p-value? You may need to rethink
the logic that led you to want a one-sided test in the first place;
particularly so if the result "in the wrong direction" has a useful
meaning, and the meaning is different from the meaning of the null
hypothesis.
To answer the question you asked, and assuming your value "p" is correct,
the p-value of your result FOR THE ONE-SIDED TEST is (1-p).
Which may, or may not, have a useful meaning.
------------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 603-535-2597
184 Nashua Road, Bedford, NH 03110 603-472-3742
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
