Convenience Methods for Setting Contrasts

This package provides modified versions of contr.treatment and contr.sum. contr.sum gains an optional base argument, analog to the one of contr.treatment, furthermore, the base argument may be the name of a factor level.

contr returns a function that calls either contr.treatment, contr.sum, etc., according to the value given to its first argument.

The contrasts method for "item" objects returns a contrast matrix or a function to produce a contrast matrix for the factor into which the item would be coerced via as.factor or as.ordered. This matrix or function can be specified by using contrasts(x)<-value

Usage

contr(type,...)
contr.treatment(n, base=1,contrasts=TRUE)
contr.sum(n,base=NULL,contrasts=TRUE)
# S4 method for class 'item'
contrasts(x,contrasts=TRUE,...)
# S4 method for class 'item'
contrasts(x, how.many) <- value
# These methods are defined implicitely by making 'contrasts' generic.
# S4 method for class 'ANY'
contrasts(x,contrasts=TRUE,...)
# S4 method for class 'ANY'
contrasts(x, how.many) <- value

Arguments

type: a character vector, specifying the type of the contrasts. This argument should have a value such that, if e.g. type="something", then there is a function contr.something that produces a contrast matrix.
...: further arguments, passed to contr.treatment, etc.
n: a number of factor levels or a vector of factor levels names, see e.g. contr.treatment.
base: a number of a factor level or the names of a factor level, which specifies the baseline category, see e.g. contr.treatment or NULL.
contrasts: a logical value, see contrasts
how.many: the number of contrasts to generate, see contrasts
x: a factor or an object of class "item"
value: a matrix, a function or the name of a function

Value

contr returns a funtion that calls one of contr.treatment, contr.sum,.... contr.treatment and contr.sum return contrast matrices. contrasts(x) returns the "contrasts" attribute of an object, which may be a function name, a function, a contrast matrix or NULL.

Examples

ctr.t <- contr("treatment",base="c")
ctr.t
#> function (n, contrasts = TRUE) 
#> contr.treatment(n = n, base = "c", contrasts = contrasts)
#> <environment: 0x560d36e19fc0>
ctr.s <- contr("sum",base="c")
ctr.h <- contr("helmert")
ctr.t(letters[1:7])
#>   a b d e f g
#> a 1 0 0 0 0 0
#> b 0 1 0 0 0 0
#> c 0 0 0 0 0 0
#> d 0 0 1 0 0 0
#> e 0 0 0 1 0 0
#> f 0 0 0 0 1 0
#> g 0 0 0 0 0 1
ctr.s(letters[1:7])
#>    a  b  d  e  f  g
#> a  1  0  0  0  0  0
#> b  0  1  0  0  0  0
#> c -1 -1 -1 -1 -1 -1
#> d  0  0  1  0  0  0
#> e  0  0  0  1  0  0
#> f  0  0  0  0  1  0
#> g  0  0  0  0  0  1
ctr.h(letters[1:7])
#>   [,1] [,2] [,3] [,4] [,5] [,6]
#> a   -1   -1   -1   -1   -1   -1
#> b    1   -1   -1   -1   -1   -1
#> c    0    2   -1   -1   -1   -1
#> d    0    0    3   -1   -1   -1
#> e    0    0    0    4   -1   -1
#> f    0    0    0    0    5   -1
#> g    0    0    0    0    0    6

x <- factor(rep(letters[1:5],3))
contrasts(x)
#>   b c d e
#> a 0 0 0 0
#> b 1 0 0 0
#> c 0 1 0 0
#> d 0 0 1 0
#> e 0 0 0 1
x <- as.item(x)
contrasts(x)
#>   b c d e
#> a 0 0 0 0
#> b 1 0 0 0
#> c 0 1 0 0
#> d 0 0 1 0
#> e 0 0 0 1
contrasts(x) <- contr.sum(letters[1:5],base="c")
contrasts(x)
#>    a  b  d  e
#> a  1  0  0  0
#> b  0  1  0  0
#> c -1 -1 -1 -1
#> d  0  0  1  0
#> e  0  0  0  1
missing.values(x) <- 5
contrasts(x)
#> Warning: contrast matrix has wrong rows, deleting it
#> NULL
contrasts(as.factor(x))
#> Warning: contrast matrix has wrong rows, deleting it
#>   b c d
#> a 0 0 0
#> b 1 0 0
#> c 0 1 0
#> d 0 0 1

# Obviously setting missing values after specifying
# contrast matrix breaks the contrasts.
# Using the 'contr' function, however, prevents this:

missing.values(x) <- NULL
contrasts(x) <- contr("sum",base="c")
contrasts(x)
#>    a  b  d  e
#> a  1  0  0  0
#> b  0  1  0  0
#> c -1 -1 -1 -1
#> d  0  0  1  0
#> e  0  0  0  1
missing.values(x) <- 5
contrasts(x)
#>    a  b  d
#> a  1  0  0
#> b  0  1  0
#> c -1 -1 -1
#> d  0  0  1
contrasts(as.factor(x))
#>    a  b  d
#> a  1  0  0
#> b  0  1  0
#> c -1 -1 -1
#> d  0  0  1