[R] posthoc tests with ANCOVA

Richard M. Heiberger rmh at temple.edu
Thu Jan 11 03:09:48 CET 2007


## The WoodEnergy example in package HH (available on CRAN) is similar
## to the example you asked about.  I have two factors and a
## covariate, and the interaction between the factors and covariate is
## significant.  I construct the multiple comparisons of factor Stove
## at each level of factor Wood at a specified value of the covariate.


## open a trellis.device() with history recording on.
## There are many plots and you will need to move among them.

require(HH)

source(paste(file.path(.path.package(package="HH")[1], "scripts"),
             "MMC.WoodEnergy-aov.R", sep="/"))
## This call prints an Error message that you can ignore because
## the relevant call is inside a try() expression.
anova(energy.aov.4)  ## source() needs a print() statement, demo() doesn't.


source(paste(file.path(.path.package(package="HH")[1], "scripts"),
             "MMC.WoodEnergy.R", sep="/"))
## The contrast matrix is developed beginning on line 91 of file
## MMC.WoodEnergy.R


## The MMC (mean-mean multiple comparisons) plots are described in R
## with ?MMC.  The MMC plots in R use the glht package.

## Both files are commented.  Please read the comments.

## Those source() commands in HH_1.17 will be replaced by demo()
## commands in the next version of HH.
##
## demo("MMC.WoodEnergy-aov", package="HH")
## demo("MMC.WoodEnergy", package="HH")


## glht is not currently able to work with aov objects that have the
## Error() function.  You will need to respecify your model formula
## using the terms() function.  See the maiz.aov example in the ?MMC
## help page.



More information about the R-help mailing list