Are there facilities in R or packages to estimate the parameters of a
(generalized) linear mixed model like this one: the design is crossed,
and response $y_{ij}$ relates to fixed and random effects through a
linear predictor
\[
\eta_{ij} = \beta x_{ij} + U_i - U_j
\]
where $U_1, U_2, \ldots$ are iid $N(0, \tau^2)$.
Any suggestions would be welcomed.
David
Professor David Firth
Dept of Statistics
University of Warwick
Coventry CV4 7AL
United Kingdom
Voice: +44 (0)247 657 2581
Fax: +44 (0)247 652 4532
Web: http://www.warwick.ac.uk/go/dfirth
structured random effects
4 messages · David Firth, Spencer Graves, Douglas Bates
Have you considered "lme"? For applications like this, I highly
recommend Pinheiro and Bates (2000) Mixed-Effects Models in S and S-Plus
(Springer). I failed to produce anything with "lme" until I read this
book.
hope this helps. spencer graves
David Firth wrote:
Are there facilities in R or packages to estimate the parameters of a
(generalized) linear mixed model like this one: the design is crossed,
and response $y_{ij}$ relates to fixed and random effects through a
linear predictor
\[
\eta_{ij} = \beta x_{ij} + U_i - U_j
\]
where $U_1, U_2, \ldots$ are iid $N(0, \tau^2)$.
Any suggestions would be welcomed.
David
Professor David Firth
Dept of Statistics
University of Warwick
Coventry CV4 7AL
United Kingdom
Voice: +44 (0)247 657 2581
Fax: +44 (0)247 652 4532
Web: http://www.warwick.ac.uk/go/dfirth
______________________________________________ R-help at stat.math.ethz.ch 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
Spencer Graves <spencer.graves at pdf.com> writes:
Have you considered "lme"? For applications like this, I highly recommend Pinheiro and Bates (2000) Mixed-Effects Models in S and S-Plus (Springer). I failed to produce anything with "lme" until I read this book. hope this helps. spencer graves
Actually lme is better suited to nested designs than to crossed designs and lme doesn't handle generalized linear mixed models. GLMM from package lme4 does handle generalized linear mixed models but does not handle crossed random effects easily. I'm working on code that will handle nested, crossed and partially crossed random effects but it will be some time before it appears in a finished package
David Firth wrote:
Are there facilities in R or packages to estimate the parameters of
a (generalized) linear mixed model like this one: the design is
crossed, and response $y_{ij}$ relates to fixed and random effects
through a linear predictor
\[
\eta_{ij} = \beta x_{ij} + U_i - U_j
\]
where $U_1, U_2, \ldots$ are iid $N(0, \tau^2)$.
Any suggestions would be welcomed.
David
Professor David Firth
Dept of Statistics
University of Warwick
Coventry CV4 7AL
United Kingdom
Voice: +44 (0)247 657 2581
Fax: +44 (0)247 652 4532
Web: http://www.warwick.ac.uk/go/dfirth
______________________________________________ R-help at stat.math.ethz.ch 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
______________________________________________ R-help at stat.math.ethz.ch 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
Douglas Bates bates at stat.wisc.edu Statistics Department 608/262-2598 University of Wisconsin - Madison http://www.stat.wisc.edu/~bates/
Thanks to Douglas and Spencer for their helpful replies. I take that as a fairly authoritative "no" to my question! The difficulty in the model I mentioned is not only the crossed design, but the "homologous" factors (ie i and j take the same values), and U_i - U_j with the *same* "U" variable appearing twice with different subscripts in the predictor. Thanks again -- I am happy to know that If I work on this I'm not reinventing what already exists. Best regards, David
On Friday, Feb 6, 2004, at 18:28 Europe/London, Douglas Bates wrote:
Spencer Graves <spencer.graves at pdf.com> writes:
Have you considered "lme"? For applications like this, I highly recommend Pinheiro and Bates (2000) Mixed-Effects Models in S and S-Plus (Springer). I failed to produce anything with "lme" until I read this book. hope this helps. spencer graves
Actually lme is better suited to nested designs than to crossed designs and lme doesn't handle generalized linear mixed models. GLMM from package lme4 does handle generalized linear mixed models but does not handle crossed random effects easily. I'm working on code that will handle nested, crossed and partially crossed random effects but it will be some time before it appears in a finished package
David Firth wrote:
Are there facilities in R or packages to estimate the parameters of
a (generalized) linear mixed model like this one: the design is
crossed, and response $y_{ij}$ relates to fixed and random effects
through a linear predictor
\[
\eta_{ij} = \beta x_{ij} + U_i - U_j
\]
where $U_1, U_2, \ldots$ are iid $N(0, \tau^2)$.
Any suggestions would be welcomed.
David
Professor David Firth
Dept of Statistics
University of Warwick
Coventry CV4 7AL
United Kingdom
Voice: +44 (0)247 657 2581
Fax: +44 (0)247 652 4532
Web: http://www.warwick.ac.uk/go/dfirth
______________________________________________ R-help at stat.math.ethz.ch 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
______________________________________________ R-help at stat.math.ethz.ch 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
-- Douglas Bates bates at stat.wisc.edu Statistics Department 608/262-2598 University of Wisconsin - Madison http://www.stat.wisc.edu/~bates/