Hi,
Using SPSS 14, if I have the following syntax to do a MANOVA repeated measures where TIME has 4
levels and I have 2 varying covariates, are there any rules for violation of normality assumption as
it is violated for all the dependent variable at all four time periods using Shapiro-Wilks.
MANOVA Y1 Y2 Y3 Y4 WITH A1 A2 A3 A4 B1 B2 B3 B4
/WSFACTORS=YEAR(4)
/CONTRAST(YEAR)=POLYNOMIAL
/wsdesign
/print=transform signif(univ).
There are 43 cases and no between subject factors. If I exclude one of the extreme cases, then
normality is passed for periods 1 and 2.
Is a transformation of the dependent variable necessary?
Paul
==================
Paul McGeoghan,
Application support specialist (Statistics and Databases),
University Infrastructure Group (UIG),
Information Services,
Cardiff University.
Tel. 02920 (875035).
=====================
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
Locked
