Daniel Perkins wrote:
>
>
> Ideally we would do an ANCOVA to test for differences in slope or
> intercepts for the different streams. However as there were repeated
> measures and unequal n and unbalanced design, I have used a linear mixed
> effect model (from nlme package in R) in the form:
>
> model <- lme (Rate ~ Temp* Stream, random = ~ Time|Replicate)
>
>
This should rather be
model <- lme (Rate ~ Temp* Stream, random = ~ 1|Time/Replicate)
Always start your model with the more parsimonious "equal slopes" assumption
denoted by 1|. When you place the Time variable as you did, it estimates
separate slopes for Time, which could be ill conditioned.
Dieter
--
View this message in context:
http://www.nabble.com/Linear-mixed-effects-model---tp25767907p25770925.html
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
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.