[R-sig-ME] Multivariate Regression with Crossed Random Effects

[Ben Bolker]

The ways to "cheat" with 2 variables (i.e., convert the data set to
long/melted format; use the index of the original observation as a
grouping variable) should in principle extend to an arbitrary number
of responses. The problem will be that estimating the 25x25
variance-covariance matrix will be difficult. (Classical MANOVA
approaches make the assumption of sphericity:
https://en.wikipedia.org/wiki/Mauchly%27s_sphericity_test )  You could
use a method (MCMCglmm, glmmTMB, lme) that allows you to constrain the
variance-covariance matrix (e.g. compound symmetric), or a Bayesian
method with a prior on the variance-covariance matrix ...

On Fri, Apr 20, 2018 at 1:14 PM, David Sidhu <dsidhu at ucalgary.ca> wrote:
> Hi All!
>
> Am I correct that it isn’t currently possible to run a mixed effects linear regression with multiple outcome variables (i.e., multivariate regression) in R? I am talking on the order of 25 outcome variables.
>
> It seems that there may be some ways to “cheat” lme4 into this, but the examples I’ve come across have all been with a pair of outcomes. Is there any way to do this with 25?
>
> Thanks!
> Dave
>
> ---
> David M. Sidhu, MSc<http://davidmsidhu.com/>
> PhD Candidate
> Department of Psychology
> University of Calgary
>
>
>
>
>
>
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models