This would be accomplished via the nlme library for mixed linear models. See Pinhiero and Bates (2000) for all relevant documentation and data applications.
Harold -----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Sent: Thursday, April 01, 2004 10:21 AM To: [EMAIL PROTECTED] Cc: [EMAIL PROTECTED] Subject: [R] general mixed model statement I am trying to analyze a general mixed model, but am confused about the model statement to use. The structure of the problem is the following: y = X b + Z u + e where X and Z are known incidence matrices for fixed and random effects respectively, b is a vector of fixed effects to be estimated, u is a vector of random effects, and e is a vector of error terms. Additionally, the covariance matrices of the random effects and error terms are given by G = g A, and R = r E where A and E are known matrices and g and r must be estimated. Presumably there is a way to specify in a model statement the known covariance structure for the random and error terms, but I cannot find the documentation I need. Please either clarify for me how to write this out or point me to the appropriate documentation that outlines the full range of model statements that are possible. Thank you very much for your help. Cheers, Brook ______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html ______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
