[R-sig-ME] Setting DDFM and Covariance Structure for Mixed Models in R

[Isaac Salfer]

Hello,

I was wondering if anyone could help solve a problem I am having with
repeated measures mixed models in R.

In our field, we frequently use repeated measures analysis and tend to use
latin-square and crossover designs often.  I have been trying to find a way
to run repeated measures mixed models that use both an autoregressive
covariance structure and Kenward-Roger denominator degrees of freedom
estimates. Unfortunately, I cannot find an R function that will allow me to
do this.  The lmer function with the lmerTest function will allow me to
adjust ddfm using the Kenward-Roger method, and the lme function (nlme
package) will let me set a correlation structure, but I have not found a
way to do both in the same model. Do you have any potential solutions for
this.

Thank you,

Isaac
---
Isaac Salfer, M.S.
Graduate Assistant
The Pennsylvania State University
(320) 296-1357

	[[alternative HTML version deleted]]