Find the row numbers in the lmat corresponding to the focus factor.
lmatRows finds the row numbers in the lmat (column numbers in the linfct in R)
corresponding to the focus factor. See
mmc for more information.
These are internal functions that the user doesn't see.
They are necessary when the design has more than one factor.
lmatContrast converts user-specified contrasts of levels of a
factor to the full
linfct matrix that carries the
information about other factors and their interactions and covariates.
lmatRows(x, focus) ## S3 method for class 'mmc.multicomp': lmatRows(x, focus) ## S3 method for class 'multicomp': lmatRows(x, focus) ## S3 method for class 'glht': lmatRows(x, focus) ## R only ## S3 method for class 'lm': lmatRows(x, focus) lmatContrast(lmat.none, contrast.matrix)
- The name of the term in the ANOVA table for which multiple comparisons are to be constructed.
lmatmatrix with the S-Plus
t(linfct)matrix with the R
multcomppackage. In both packages the matrix is the one used for estimating the group means.
- Matrix of column contrasts for a factor. The columns are the contrasts, the rows are the levels of the factor.
MMC function are based on
glht in R and on
in S-Plus. The two packages have different conventions for specifying
the linear contrasts. The
lmatRows function gives appropriate
values in each system.
lmatRows, vector of row numbers of the
lmat, the matrix of linear contrasts defining the comparisons of interest. For
lmatContrast, a linear contrast matrix that follows the conventions of the multiple comparisons package. It has columns for each contrast specified by the input
contrast.matrixand rows as needed for the other terms in the model.
## catalystm example ## See ?MMC for more on this example catalystm <- read.table(hh("datasets/catalystm.dat"), header=FALSE, col.names=c("catalyst","concent")) catalystm$catalyst <- factor(catalystm$catalyst, labels=c("A","B","C","D")) catalystm1.aov <- aov(concent ~ catalyst, data=catalystm) catalystm.mmc <- if.R(r=glht.mmc(catalystm1.aov, linfct = mcp(catalyst = "Tukey")), s=multicomp.mmc(catalystm1.aov, plot=FALSE)) dimnames(catalystm.mmc$mca$lmat)[] lmatRows(catalystm1.aov, focus="catalyst") ## user-specified contrasts catalystm.lmat <- cbind("AB-D" =c( 1, 1, 0,-2), "A-B" =c( 1,-1, 0, 0), "ABD-C"=c( 1, 1,-3, 1)) dimnames(catalystm.lmat)[] <- levels(catalystm$catalyst) zapsmall(lmatContrast(catalystm.mmc$none$lmat, catalystm.lmat))