[R-sig-ME] RE : Unbalanced design mixed models

Boulanger, Yan Yan.Boulanger at RNCan-NRCan.gc.ca
Sat Apr 20 20:40:39 CEST 2013


Thanks Douglas,

But statistically speaking, including the plots with only one individual in this context is incorrect right?

Many thanks!

Yan
________________________________
De : dmbates at gmail.com [dmbates at gmail.com] de la part de Douglas Bates [bates at stat.wisc.edu]
Date d'envoi : jeudi 18 avril 2013 13:06
À : Boulanger, Yan
Cc: r-sig-mixed-models at r-project.org
Objet : Re: [R-sig-ME] Unbalanced design mixed models

On Wed, Apr 17, 2013 at 1:14 PM, Boulanger, Yan <Yan.Boulanger at rncan-nrcan.gc.ca<mailto:Yan.Boulanger at rncan-nrcan.gc.ca>> wrote:
Hi folks,

This seems a very (I mean very...) basic mixed model question but I would like to have your feeling about this. I start from scratch with mixed models. I'm fitting this very simple mixed model:

fm1 <- lmer(dbh_tree ~ log(age_tree) + (1|plot_name), PICE.MAR_tree)

where dbh_tree is the diameter at breast height of a tree, age_tree the age of the tree at bh, plot_name is the plot where the tree was sampled and PICE.MAR_tree, my dataset. This is not an experimental setup where a fixed number of trees was sampled per plot. Indeed, some plots have as high as 150 trees (very few...) whereas others has only 1... At that is the (well one of the...) problem. How may I fit a mixed model where, in several cases, well, maybe 50%, there is only 1 tree per level of the random factor ? So, no variation within the random factor... I could forget the random factor but of course, this would lead to "partial" pseudoreplication. On the other hand, I could drop all plots with only one tree but this would discard about half of the plots. Am I right when I say that the coefficients (for the fixed variables) are unbiased when not considering the random factor ? Indeed, I'm not interested in CI but "only" to fixed variable coefficients.

I think you will find that there is very little difference in the model fits whether you include or exclude the single-observation groups.  Try it and see.



More information about the R-sig-mixed-models mailing list