Thanks for the example, but I'm still not sure from this example how to see
the pairwise comparisons for the interaction. For example, if I have two
factors, X and Y; and X has 2 levels, A and B, and Y has 3 levels, 1, 2, and
3, a TukeyHSD would give the following comparisons with p-values for each:
factor X
A-B
factor Y
1-2
1-3
2-3
X:Y
A:1 - A:2
A:1 - A:3
A:2 - A:3
A:1 - B:1
A:1 - B:2
A:1 - B:3
A:2 - B:1
........etc.
But if I add a covariate in addition to these two factors, TukeyHSD won't
work (because it doesn't recognize the covariate as a factor).
With the maiz example in ?MMC, it shows the differences between hybrids, but
doesn't show all the differences between nitrogen levels within and between
hybrids, unless I'm not seeing something (I must admit, the tie-breaker plot
was new to me and I'm still not entirely sure I understand it). glht and
glht.mmc both seem to only allow one factor in the
linfct=mcp(factor="Tukey") argument. For example, glht.mmc(maiz2.aov,
linfct=mcp(hibrido:nitrogeno="Tukey")) doesn't work.
I apologize if my confusion stems from a lack of knowledge of the
statistical underpinnings of an ANCOVA, but it seems like there should be a
way to get the same types of comparisons that TukeyHSD gives.
-Eric Scott
On Mon, Mar 15, 2010 at 8:19 AM, RICHARD M. HEIBERGER <r...@temple.edu>wrote:
> Please see the maiz example in ?MMC in the HH package.
>
> maiz is the last example in the help file. Keep going all the way to the
> end of
> the help file. See also the
>
> demo("MMC.WoodEnergy-aov", "HH")
> These examples show how to use glht in the presence of interactions and
> covariates.
>
> Rich
>
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
