|Date: ||Thu, 29 Jan 2009 06:56:35 -0800|
|Reply-To: ||paul wilson <paulwilsn@YAHOO.COM>|
|Sender: ||"SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>|
|From: ||paul wilson <paulwilsn@YAHOO.COM>|
|Subject: ||Re: Independent Samples t Test question|
|Content-Type: ||text/plain; charset=iso-8859-1|
Thanks a lot Peter.
Sorry to hear you lost your job.
I'm sure you won't have too much trouble finding work given your great skillset.
From: Peter Flom <firstname.lastname@example.org>
To: paul wilson <email@example.com>; paul wilson <paulwilsn@YAHOO.COM>; SAS-L@LISTSERV.UGA.EDU
Sent: Thursday, January 29, 2009 9:48:57 AM
Subject: Re: Independent Samples t Test question
paul wilson <firstname.lastname@example.org> wrote
>Thanks for your feedback Peter!
>As always, very informative and useful.
You're welcome! Glad to be helpful.
>Could you please mention a few most commonly used nonparametric tests and SAS procedures I'd >need to use in order to run them?
Unfortunately, my books are at the office of a job I just lost .... they are letting me leave them there while I search for work, but I am home. One good book is Hollander and Wolfe, Nonparametric Statistical Methods. I'm not sure if you're associated with a university, but any good research library should have it.
That said, the most obvious alternative is the Mann Whitney U test, although this is a test of the entire distribution, not just the mean (or other measure of central tendency). This may be what you want. This can be done with PROC NPAR1WAY.....
PROC NPAR1WAY data = mydata wilcoxon;
Peter L. Flom, PhD
www DOT peterflom DOT com