[R] syntex about a nested mixed linear model

JongJoo Kim kimjj at email.arizona.edu
Thu Sep 2 23:46:31 CEST 2004

I am a novice R user, and have been in trouble to get the right mixed
model syntax in microarray analyses.

There are three factors: Dye(2 levels), Temperature(3 levels) and
Array(3 for each Temperature with a total of 9 arrays). I want to treat
array as random, and to regard array variation different between

So the model I want to seek is:

Y = Dye + Temp + Dye + Temp*Dye + Array(Temp) + Dye*Array(Temp).

For F tests of Dye and Dye*Temp, then denominator factor is 
Dye*Array(Temp). For F test of Temp, then denominator factor is

I wrote this syntax to fit the above model by typing:

R2.0<-lme(dsnx.0 ~ temp+Dye+temp*Dye, random = list(
Dye*Array(Temp)=pdDiag(~-1+temp*Dye),  Arra=pdDiag(~-1+temp) ) ).

But there is syntax error message.
To obtain one solution, I typed

which created another factor, int.dye for 'Dye*Array(Temp)', and I

>R2.0<-lme(dsnx.0 ~ temp+Dye+temp*Dye, random = list(
int.dye=pdDiag(~-1+temp*Dye),  Arra=pdDiag(~-1+temp) ) )

It worked but the degree of freedom for int.dye is 12 instead of 6 <=

Could you solve the syntax to fit the right model for this nexted mixed
Thanks so much for your guidance.
JongJoo Kim, Ph.D.

243 Shantz Building
Department of Animal Science
University of Arizona
Tucson, AZ 85721
Tel) 520-621-9757
Fax) 520-621-9435
kimjj at email.aizona.edu

More information about the R-help mailing list