Hi Everyone,
Im trying to figure out how to get R to analyze this experiment properly. I
have a series of subjects each with two legs. Within each leg there are two
bones that I am interested in. There are also two treatments that I am
interested in. That results in four different combinations of treatments.
Obviously, since the subjects only have two legs, they cant receive each
combination of treatment. The groups are unbalanced so I cant use aov. As I
understand it, lme should work but I am having a tough time figuring out what
to use as a random term. Is this correct?
x.lme <- lme(effect~bone*treatment1*treatment2, random= ~1|subject, data=x)
anova(x.lme)
Ive tried a number of different random terms and get very similar results (and
even get similar results running aov) but Id like to know what the proper way
of doing it is.
My next question is how to do post hoc tests on this. One website recommends
something like this from multcomp:
summary(glht(am2,linfct=mcp(myfactor="Tukey")))
But apparently this doesnt work with interactions. With my data, I get a
significant three-way interaction. If I run TukeyHSD after an aov (ignoring
the repeated measures) I would get a series of p values for all the different
combinations of treatments and bones. Is there a way to do this with lme?
Thank you in advance for any help.
Doug Bourne
[[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.
