I have done ancova with categorical and continuous predictor variables.
The categorical predictor variable shows significant effect on the dependent
variable.
I would like to do a post-hoc test to see which groups in the categorical
variable differ.
I have explored Tukey test in multcomp package. My study is similar to the
"litter data". In the code it's mentioned that the contrast matrix also has
some trends like otrend, atrend and ltrend.
otrend = c(-1.5, -0.5, 0.5, 1.5),
atrend = doselev - mean(doselev),
ltrend = log(1:4) - mean(log(1:4)))
Here are my questions:
Are this trends absolutely essential for conducting the Tukey test?
If yes, how can I set these trends?
thanks,
mahua
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
