mratios (version 1.4.2)

contrMatRatio: Creates numerator and denominator contrast matrices for ratio-based hypotheses for common multiple comparison and trend test problems

Description

Creates numerator and denominator contrast matrices for some common multiple comparison and trend test problems. These matrices are internally used by the sci.ratio and simtest.ratio functions. The contrMatRatio function is a modification of the function contrMat (multcomp).

Whether the given definitions of contrast matrices for trend test problems in terms of ratios make sense and how they are to be interpreted is to be discussed.

Usage

contrMatRatio(n, type = c("Tukey", "Dunnett", "Sequen",
 "AVE", "GrandMean", "Changepoint", "Marcus", "McDermott", 
 "Williams", "UmbrellaWilliams"), base = 1)

Arguments

n

integer vector of sample sizes

type

the type of multiple contrasts

• "Dunnett": many to one comparisons, with the control group in the denominator

• "Tukey": all-pair comparisons

• "Sequen": comparison of consecutive groups, where the groups of lower order is the denominator

• "AVE": comparison of each group with average of all others, where the average is taken as denominator

• "GrandMean": comparison of each group with grand mean of all groups, where the grand mean is taken as denominator

• "Changepoint": ratio of averages of groups of higher order divided by averages of groups of lower order

• "Marcus": Marcus contrasts defined for ratios

• "McDermott": McDermott contrasts for ratios

• "Williams": Williams contrasts for ratios

• "UmbrellaWilliams": Umbrella-protected Williams contrasts for ratios, i.e.a sequence of Williams-type contrasts with groups of higher order stepwise omitted

base

a single integer specifying the control (i.e. denominator) group for "Dunnett"-type contrasts for calculating the ratios to the control

Value

A list containing:

numC

the (named) numerator contrast where rows correspond to contrasts

denC

the (named) denominator contrast where rows correspond to contrasts

rnames

a character vector with names of the contrasts

and the type of contrast as attr.

Details

This is a simple adaption of the contrMat function in the package multcomp for ratio hypotheses.

See Also

contrMat(multcomp)

Examples

# NOT RUN {
library(mratios)

n=c(A=10,B=20,Z=10,D=10)

contrMatRatio(n=n, type="Dunnett", base=1)
contrMatRatio(n=n, type="Dunnett", base=3)

contrMatRatio(n=n, type="Tukey")
contrMatRatio(n=n, type="Sequen")
contrMatRatio(n=n, type="AVE")
contrMatRatio(n=n, type="GrandMean")
contrMatRatio(n=n, type="Williams")
contrMatRatio(n=n, type="UmbrellaWilliams")
# }