Re: Shapiro-Wilks Statistic

Posted by Art Kendall on
URL: http://spssx-discussion.165.s1.nabble.com/Shapiro-Wilks-Statistic-tp5739693p5739709.html

You said you had ordinal data.  When I have reviewed manuscripts where other
reviewers have raised the issue of level of measurement this is what I have
suggested.
Try CATREG in SPSS.  CATREG does a test between models with different
assumptions about measurement level. See whether there is a meaningful
difference between MODEL fits with  ORDINAL specification and INTERVAL
specifications.  (You might also try a NOMINAL specification.)
If there is no meaningful difference in fits, use the interval level results
and add a footnote that CATREG showed no meaningful difference in fits when
ORDINAL was specified.



YMMV but I have tried this CATREG approach a dozen or so times and never
found a meaningful difference between the fits.

also see CATPCA in help



-----
Art Kendall
Social Research Consultants
--
Sent from: http://spssx-discussion.1045642.n5.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
Art Kendall
Social Research Consultants