[S] decomposing variance components

Bill Shipley (bshipley@courrier.usherb.ca)
Tue, 3 Mar 1998 08:50:37 -0500


I would like to know how one decomposes the variance components of a factor
into its levels. An example will clarify this. Let the model be:

varcomp(Y~F/S)
where F is a fixed factor with 4 levels and S is a random factors with two
levels, in a completely nested design (errors are nested in S). I want to
estimate the variance components of S within each of the four levels of F
as can be done in SAS. Thus, I want to get as output:

Source variance component
S in F level 1 ?
S in F level 2 ?
S in F level 3 ?
S in F level 4 ?
error in S ?

I have compared the output of SAS with that for SPLUS (restricted maximum
likelihood) and the total variance components of S and error agree.
However, in SAS I can also get the components of S and error for each level
of F but this is not provided by varcomp()
Any help is welcome!
Bill Shipley
Departement de Biologie
Universite de Sherbrooke
Sherbrooke (Quebec)
CANADA J1K 2R1
bshipley@courrier.USherb.ca
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