[R-sig-ME] Post hoc tests with lme
Gang Chen
gangchen6 at gmail.com
Thu Apr 17 17:41:50 CEST 2008
Thanks for the suggestion, Somon! I did try glht from multcomp
package, but the problem is that for the hypothesis
H0: TypeT1 =0 and TypeT2 = 0
it gives results for two separate hypotheses H01: TypeT1 =0 and H02:
TypeT2 = 0, not exactly one statistic for the original hypothesis H0.
So my question is, how can I get only one statistic for H0? Any more
suggestions?
Thanks,
Gang
> library(nlme)
> fm <- lme(effort~Type-1, data=ergoStool, random=~1|Subject)
> library(multcomp)
> summary(glht(fm, linfct=c("TypeT1=0", "TypeT2=0")))
Simultaneous Tests for General Linear Hypotheses
Fit: lme.formula(fixed = effort ~ Type - 1, data = ergoStool, random = ~1 |
Subject)
Linear Hypotheses:
Estimate Std. Error z value p value
TypeT1 == 0 8.556 0.576 14.85 <1e-10 ***
TypeT2 == 0 12.444 0.576 21.60 <1e-10 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
(Adjusted p values reported -- single-step method)
On 4/16/08, Simon Blomberg <s.blomberg1 at uq.edu.au> wrote:
> Try glht in package multcomp.
>
> Simon.
>
>
> On Wed, 2008-04-16 at 12:00 -0400, Gang Chen wrote:
Using the "ergoStool" data cited in Mixed-Effects Models in S and
S-PLUS by Pinheiro and Bates as an example, we have
========
> library(nlme)
> fm <- lme(effort~Type-1, data=ergoStool, random=~1|Subject)
> summary(fm)
Now suppose I want to test the following hypothesis
H0: TypeT1 =0 and TypeT2 = 0
I've tried estimable() and glh.test() in package gmodels, esticon() in
package boBy, and linear.hypothesis() in package car, but it seems
none of them would work with objects from lme.
More information about the R-sig-mixed-models
mailing list