1
$\begingroup$

I am working with trees that were fertilized in a full factorial design (N x P x K) in plots that are replicated four times. I currently have a mixed effects model with this structure:

> library("nlme")
> model <- lme(growth ~ P*N*K, data=Lars_noNA, random=~1|rep/block/plot4040)
> summary(model)

Where rep = replicate, block is part of the blocking layout, and plot4040 is a plot that received a nutrient treatment. Now I want to growth by individuals measured multiple times over 15 year and but I don't know if this is the way to handle the error associated with the repeated measures.

>library (nlme)
>model <- lme (AGBnew ~ P*N*K+year, data=mydata_sorted1, 
               random=~1|rep/block/plot4040/individual/year) 
>summary(model)
$\endgroup$
2
  • $\begingroup$ If you are only asking how to use R, this question would be off-topic for CV. It might be a good question for the r-help-listserv. Can you clarify? $\endgroup$ Nov 19, 2014 at 16:15
  • 2
    $\begingroup$ well, while part of it is about using r, the fundamental question is about how you properly structure the model for nested effects and repeated measurements for handling the error correctly. I apologize if this is not quite along the lines of this forum. I should also say, that the r model works, but I am not sure that is doing what I want it to statistically. $\endgroup$
    – Annette
    Nov 19, 2014 at 18:32

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.