[R] lme posthoc comparisons in R

Romina Rader romina.rader at jcu.edu.au
Thu Apr 15 04:43:19 CEST 2010

Hi there, I was hoping to post this message.  Im hoping I;ve got the right spot?!
Hi there, 
sorry for basic question but im very new to R.  Im trying to run a lme model with two categorical variables, each having 6 (for the explanatory variable C.f) and 5 levels (for expl. variable D.f) respectively.  The lme runs fine, summary and anova commands are ok.  But now i've tried running posthoc comparisons using the glht command in the multcomp package but seem to have an error with my data labelling maybe?  it doesnt seem to recognise my factor levels even though I have stated them. if i can do somekind of tukeys or LSD's that would be wonderful! 

M1lme <- lme(logA ~ C.f * D.f, random = ~1 | F.f, data = rfreq) 
> summary(M1lme) 

> anova(M1lme) 
           numDF denDF  F-value p-value 
(Intercept)     1    87 75.50639  <.0001 
C.f             5    87  5.52555   2e-04 
D.f             4    87 22.74062  <.0001 
C.f:D.f        20    87  3.77657  <.0001 

#so now I will try to do posthoc comparisions (if i've done it right?) 

> posthoclme <- glht(M1lme, linfct = mcp(D.f = "Tukey")) 
Error in `[.data.frame`(mf, nhypo[checknm]) : undefined columns selected 

#im not sure why im getting this error, can someone please offer some advice? 
thanks so much 

More information about the R-help mailing list