[S] help with variance components model

Bill Shipley (bshipley@courrier.usherb.ca)
Mon, 30 Mar 1998 11:18:43 -0500

I am trying to fit a variance components model with Splus, but do not
understand the varcomp() function. I have a nested sampling design:
2 leaves each from an individual plant, 3 plants per species and 21 species.
Note that the data set is not completely balanced due to missing values.
Now, after making the three variable (species, ind, leaf) random factors, if
I specify:

fit<-varcomp(Y~species/ind, method="reml")

I had assumed that the leaf level would be what varcomp calls "residuals",
but this is not the case, since if I specify:

fit<-varcomp(Y~species/ind/leaf, method="reml")

then varcomp computes the variance components at each nested level PLUS a
"residuals". What is going on? What variance does the "residuals"
represent in this second model?

Bill Shipley
Departement de Biologie
Universite de Sherbrooke
Sherbrooke (Quebec)
voix: 819-821-8000 poste 2079
telecopieur: 819-821-8049
Visitez notre site WEB : http://www.usherb.ca/SCES/BIO/index.html
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news