R help - Jan 2012 - problems with glht for ancova

I've run an ancova, edadysexo is a factor with 3 levels,and log(lcc) is the
covariate (continous variable)
I get this results

> ancova<-aov(log(peso)~edadysexo*log(lcc))
> summary(ancova)
                    Df Sum Sq Mean Sq  F value Pr(>F)    
edadysexo            2 31.859 15.9294 803.9843 <2e-16 ***
log(lcc)             1 11.389 11.3887 574.8081 <2e-16 ***
edadysexo:log(lcc)   2  0.063  0.0317   1.6021 0.2025    
Residuals          509 10.085  0.0198                    

Then, I tried to do a post-hoc using glht from multcomp package, but,
because the interaction it's not siginificant i did it just for the factor 

> summary(glht(ancova, linfct=mcp(edadysexo="Tukey")))
         Simultaneous Tests for General Linear Hypotheses

Multiple Comparisons of Means: Tukey Contrasts


Fit: aov(formula = log(peso) ~ edadysexo * log(lcc))

Linear Hypotheses:
             Estimate Std. Error t value Pr(>|t|)
M - H == 0    -1.8218     1.1111  -1.640    0.230
SUB - H == 0  -0.9298     1.1957  -0.778    0.717
SUB - M == 0   0.8921     1.1130   0.801    0.702
(Adjusted p values reported -- single-step method)

Mensajes de aviso perdidos
In mcp2matrix(model, linfct = linfct) :
  covariate interactions found -- default contrast might be inappropriate


Two question:
1) Why I don't get differences in edadysexo when i got it in the ancova
2) About the warning message. Why R said "covariate interactions
found" of i
didn't get it in the ancova

Next, i tried to made glht with the interaction, but, obviously, i got an
error because Tukey just work with factors.  

> summary(glht(ancova, linfct=mcp(edadysexo*log(lcc)="Tukey")))
Error: inesperado '=' en "summary(glht(ancova,
linfct=mcp(edadysexo*log(lcc)="

What should i do?

Thanks in advance

-----
Mario Garrido Escudero
PhD student
Dpto. de Biolog?a Animal, Ecolog?a, Parasitolog?a, Edafolog?a y Qca. Agr?cola
Universidad de Salamanca
--
View this message in context:
http://r.789695.n4.nabble.com/problems-with-glht-for-ancova-tp4284908p4284908.html
Sent from the R help mailing list archive at Nabble.com.

I answer myself, perhaps it can be useful to anyone.

The problem is that I tried to run a psot hoc test before i get the minimal
model by deleting the interaction, 

if I do it:
> ancova2<-aov(log(peso)~edadysexo+log(lcc))
> anova(ancova,ancova2)
  Res.Df    RSS Df Sum of Sq      F Pr(>F)
1    509 10.085                           
2    511 10.148 -2 -0.063484 1.6021 0.2025

It's correct, there is no differences between models. And now i can run a
post hoc test
> summary(glht(ancova2, linfct=mcp(edadysexo="Tukey")))
             Estimate Std. Error t value Pr(>|t|)    
M - H == 0    0.15120    0.01761   8.588   <1e-05 ***
SUB - H == 0 -0.01584    0.02659  -0.596    0.812    
SUB - M == 0 -0.16704    0.03248  -5.144   <1e-05 ***
 (Adjusted p values reported -- single-step method)
>Two question: 
>1) Why I don't get differences in edadysexo when i got it in the ancova 
Wthi the minimal model i get it
>2) About the warning message. Why R said "covariate interactions
found" of
i didn't get it in the ancova 
Because in the first model "edadysexo" was in an interaction.

I hope this will be useful Mario




-----
Mario Garrido Escudero
PhD student
Dpto. de Biolog?a Animal, Ecolog?a, Parasitolog?a, Edafolog?a y Qca. Agr?cola
Universidad de Salamanca
--
View this message in context:
http://r.789695.n4.nabble.com/problems-with-glht-for-ancova-tp4284908p4288226.html
Sent from the R help mailing list archive at Nabble.com.

Thanks very much

-----
Mario Garrido Escudero
PhD student
Dpto. de Biolog?a Animal, Ecolog?a, Parasitolog?a, Edafolog?a y Qca. Agr?cola
Universidad de Salamanca
--
View this message in context:
http://r.789695.n4.nabble.com/problems-with-glht-for-ancova-tp4284908p4288227.html
Sent from the R help mailing list archive at Nabble.com.