Hello,
I am trying to do a manova test in r, and have used the "manova" function to
test differences between two dependent variables. The results were
significant for the whole model, but the sources I've read say that in order
to do a post-hoc multiple comparison, I have to do separate aovs for each
dependent variable, then call the TukeyHSD function.
I have used the TukeyHSD with success in the past, but now when I try it,
the only output I get says "height." I want to find out whether the
dependent variable, "sum_enemies", is different across plant species
"early_plant", and which plant species are significantly different from ea
other.
Below is the code i used to call the TukeyHSD:
early_anova=aov(formula=early_data$sum_enemies~early_plant, data=early_data)
early_tukey=TukeyHSD(early_anova,"early_plant", ordered=TRUE)
When I ask R to plot the results for my tukey test (which I've named
"early_tukey"), it says "Error in vcov.default(early_tukey) :
object does not have variance-covariance matrix."
I'm not sure why I'm getting this error. I was able to print the var-covar
matrix for the aov, but not for the tukey. Whenever I've used TukeyHSD in
the past, I had no problems.
Is there an apparent error in the code I've written above? Or can anyone
suggest another place I can look?
Thanks,
Molly
[[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.
