On Thu, 26 Sep 2002, Jan Malte Wiener wrote:
> i am looking for a way to correct for ties in signed-rank tests.
> whats the easiest way to do so?
Easiest? Use a statistical package that does it. SPSS does, for example,
and I believe SAS does. Reference manuals for other packages are not at
hand at the moment (I'm in the middle of moving from house to apartment).
If you aren't using a statistical package (and why not, then? one
wonders), simply convert the original data to ranks (easily done in any
standard package, and in the absence of a package, easily done by a
standard routine in your computer). Then conduct a t-test on the ranks.
(This has been shown to be equivalent to the Wilcoxon signed-rank test,
aka the Mann-Whitney test, for example.)
-- Don.
-----------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816
[Old address: 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/ .
=================================================================
