nonparametric ANCOVA in SPSS

[Scott Roesch]

Hi all:

 

Can anyone point me to a nonparametric version of ANCOVA that is available in SPSS (version 17 and beyond)? Thanks!

 

Scott

[2freet]

Maybe you'll find what you're looking for under /Analyze/Nonparametric Tests.
The Kruskal-Wallis test could be a good choice.

2freet



--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/nonparametric-ANCOVA-in-SPSS-tp5721459p5721461.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Rich Ulrich]

Is there *anyone*  who has something like what you are
asking about?

"Nonparametric" usually means "based on the rank-order
transformation."  I generally have preferred other transformations,
because they have a chance of achieving equal intervals, and
thus are more usable for analyses with several variables,
including ANCOVA. 

There are papers that suggest you can (sometimes) get
robustness if you follow a rank-transform by doing a logistic
or normal transform.  That sort of thing is done is item-
scaling paradigms.   But I don't remember it being a part of
some other package.

--
Rich Ulrich

---

Date: Fri, 2 Aug 2013 12:10:48 -0700
From: [hidden email]
Subject: nonparametric ANCOVA in SPSS
To: [hidden email]

Hi all:

 

Can anyone point me to a nonparametric version of ANCOVA that is available in SPSS (version 17 and beyond)? Thanks!

 

Scott