[EMAIL PROTECTED] wrote:
Hello,
I'm looking for F/OS software that does statistical tests of
significance, specifically the sign test, paired t test, paired
Wilcoxon test (and maybe Kendall's tau). Ideally, I would like
to be able to simply provide n pairs of observations, specify
which test I want to run, and get back the p value.
Can you suggest some specific package that will be easy to use?
Should I just use R, or is there anything more lightweight that
I could use?
R is certainly the best one. There are some others with GUI
interfaces... (a bit more of dependencies) ... .
There are of course many packages which can be easily (?!) rewritten for
the purpose. Maxima can be adapted ... the code is in lisp. But can be
managed with pipes. There are many good advanced calculator programs
which can also be modified for the purpose. Yacas is relatively light
weight ....
Best,
A. Mani
Member, Cal. Math. Soc
--------------------------------------------------------------------------------------------
Doubt Everything
---------------------------------------------------------------------------------------------
--
To unsubscribe, send mail to [EMAIL PROTECTED] with the body
"unsubscribe ilug-cal" and an empty subject line.
FAQ: http://www.ilug-cal.org/node.php?id=3
