[R-sig-ME] lme for split-plot

[Andrew Robinson]

I think that you should leave them in the model. They reflect the experimental design, and their inclusion will help your fixed effects estimates and inference do the same!

I hope that this helps,

Andrew

---

Andrew Robinson. 
Program Manager, ACERA
Senior Lecturer, Applied Statistics
The University of Melbourne. 

On 28/07/2010, at 8:31 AM, Etienne Laliberté <etiennelaliberte at gmail.com> wrote:

> I'm analyzing experimental data from a split-plot design, with two
> blocks, each block containing five whole plots, and each whole plot
> containing three subplots.
> 
> The multilevel structure of the design dictates the following random
> structure (in the case of a random intercept model):
> 
> lme(...., random = ~ 1 | block / wholeplot, ...)
> 
> However, if, for a given model, the random effects end up being
> incredibly small, e.g.
> 
> Random effects:
> Formula: ~1 | block
>         (Intercept)
> StdDev: 4.639022e-06
> 
> Formula: ~1 | wholeplot %in% block
>         (Intercept)  Residual
> StdDev: 2.256742e-09 0.1911715
> 
> Is it still better to leave them in the model, or should I exclude them
> and use gls() instead?
> 
> Many thanks,
> 
> Etienne
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models