[R] testing differences between slope differences with lme
A.Robinson at ms.unimelb.edu.au
Tue Apr 10 01:47:33 CEST 2007
I would construct vectors that represent the linear contrasts of
interest, and test them using the estimable() function of the gmodels
On Mon, Apr 09, 2007 at 07:18:54PM -0400, Dede Greenstein wrote:
> i have a mixed effect model which gives slope and intercept terms for 6
> groups (diagnosis (3 levels) by risk group(2 levels)). the fixed part of
> the model is --
> brain volume ~ Diagnosis + Risk Group + (Risk Group * age : Diagnosis) - 1
> thus allowing risk group age/slope terms to vary within diagnosis and
> omitting a nonsignificant diagnosis by risk group intercept (age was
> centered) interaction.
> i am interested in whether differences in risk groups' developmental
> trajectories are different for different diagnoses.
> the last three (of 10) fixed effect estimates are estimates for the
> age/slope differences between risk groups for the 3 diagnostic groups.
> my question is this -- how do i test if the 3 differences are statistically
> different from each other?
> i can do this in SAS but the answer in R is eluding me.
> thanks in advance,
> R-help at stat.math.ethz.ch mailing list
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
Department of Mathematics and Statistics Tel: +61-3-8344-9763
University of Melbourne, VIC 3010 Australia Fax: +61-3-8344-4599
More information about the R-help