[R] Kronecker product in PROC MIXED and lme

Giovanni Parrinello parrinel at med.unibs.it
Mon Aug 6 09:48:58 CEST 2007


Dear All,
I am trying to translate some code in SAS about longitudinal data in R.
I have found among the predefined covariance structures for repeated 
measures in the PROC MIXED the following:
type=UN at AR(1).
'Kronecker product structure of the variance–covariance matrixi =dimni 
(E⊗V),V, where
 and V, respectively, are (q×q) and (p×p) positive denite matrices. 
The matrix  represents the variance–covariance matrix between the 
measurements
on all response variables at a given time point. It is assumed that it 
does not depend
on a particular time point and is the same for all time points. The 
matrix V is the correlation
matrix of the repeated measures on a given response variable, and is 
assumed to be the same
for all response variables.'
Is it possible?
TIA
Giovanni

-- 
dr. Giovanni Parrinello
External Lecturer
Medical Statistics Unit
Department of Biomedical Sciences
Viale Europa, 11 - 25123 Brescia Italy
Tel: +390303717528
Fax: +390303717488
email: parrinel at med.unibs.it



More information about the R-help mailing list