Violation of ANCOVA equal slopes assumption- now what?
Message posted by Dave (via 192.231.113.84) on October 2, 2001 at 5:19 PM (ET)

What do you do if the slopes of the groups are not equal? I assume you can use ANCOVA to ask if the treatment had an affect on the slopes, but what about the overall effect? Can I just fall back on ANOVA? I have a book which says to multiply the dummy grouping variable by the covariate and add this term into the model, or something like that which makes no sense.