[R-sig-ME] Ordinal Package and post hoc test

[David Duffy]

On Mon, 28 May 2012, fernando barbero wrote:

>  fm1<-clmm(leaf~population+(1|population:family),data=d,threshold"flexible",
<            link="probit",Hess=TRUE)

> now I want to asses differences within populations, as visual inspection of
> the data suggests that one population has got more seedlings in the A
> category than the other 3 populations. I am thinking in something like the
> glht function of the multcomp package (tukey<-glht(fm1,

How about
pop1 <- d$population == "pop1"
fm2  <- clmm(leaf~ pop1 +(1|pop1:family), data=d,
              threshold"flexible", link="probit",Hess=TRUE)
anova(fm1, fm2), with or without a Bonferroni correction, or use AIC.

-- 
| David Duffy (MBBS PhD)                                         ,-_|\
| email: davidD at qimr.edu.au  ph: INT+61+7+3362-0217 fax: -0101  /     *
| Epidemiology Unit, Queensland Institute of Medical Research   \_,-._/
| 300 Herston Rd, Brisbane, Queensland 4029, Australia  GPG 4D0B994A v