Glen:  see below.

On Fri, 28 Jun 2002, Glen Barnett wrote, in response to my comment:

> > Look in your favorite ANOVA text for the chapter on post hoc
> > comparisons, and in particular the method of Scheffe' (called in some
> > texts the "S-method").  The linear combination you describe is
> > properly called a "contrast" in this context, a contrast being merely
> > a linear combination of means with the constraint that the
> > coefficients of the means sum to 0 (as your +0.5, +0.5, -1.0 do).
>
> A contrast needn't be a post hoc comparison. Often a particular contrast
> is the primary comparison of interest right from the start. In that
> circumstance, the Scheffe thing won't be appropriate.
>
> Glen

Please re-read my complete response.  The "t" value obtained is the same
in any case;  the only difference between an a priori test (or "planned
comparison") and a post hoc test (Scheffe') is the critical value against
which one compares the test statistic "t":  in particular, whether one
uses a critical value from "Student"'s t distribution or from (the square
root of) Snedecor's F distribution with m-1 d.f. for the numerator.

-- Don.
 -----------------------------------------------------------------------
 Donald F. Burrill                                            [EMAIL PROTECTED]
 184 Nashua Road, Bedford, NH 03110                       (603) 471-7128


.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to