Issues using varcomp

General
1

Hi All,

I am trying to calculate percent variation across scales for plants (individual leaves in a plant, between plants in a site, and site between site). I am getting confused as for some reason my code is equaling more than 1, not by much its comes out to be 1.09 but I know that there has to be an error. Has anyone run into this before? Or possibly have any suggestions? Thank you

####variation

m <- lme(log10(nitrogen) ~ 1, random = ~ 1|site/plant, data=pitcher.env, na.action = na.omit)
d <- varcomp(m, TRUE, TRUE)
plot(d)
print(d)
site plant Within
0.4240241 0.6740207 1.0000000
attr(,"class")
[1] "varcomp"

2

Could you edit in a reprex?

Please see the FAQ: What's a reproducible example (`reprex`) and how do I do one? Using a reprex, complete with representative data will attract quicker and more answers.

For this

library(WHICH ONE?)
# GET PITCHER.ENV WHERE?
m <- lme(log10(nitrogen) ~ 1, random = ~ 1|site/plant, data=pitcher.env, na.action = na.omit)
d <- varcomp(m, TRUE, TRUE)

will help others to replicate the problem; otherwise, the only thing that can easily be offered is a tour of help(lme)'s signature and return value and working the examples.

3

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.