I got criticized by a reviewer that "equidistant time points are a crucial
assumption of the repeated measures ANOVA". Is this correct?
It was always my understanding that when it comes to the *interpretation*
of trends over time (e.g., polynomial contrasts), non-equidistance must be
taken into account, but as long as the usual assumptions (sphericity,
homogeneity of covariance matrices etc.) are met, the repeated measures
ANOVA (i.e., testing mean differences) should not depend on equidistant
time points.
Thank you for any dis/confirmation!!!
=====================
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
