contr-wsum: Contrast matrices
In vcrpart: Tree-Based Varying Coefficient Regression for Generalized Linear and Ordinal Mixed Models

Returns a category-weighted contrast matrix

1	contr.wsum(x, weights = rep.int(1.0, length(x)), sparse = FALSE)

`x`	a factor vector
`weights`	a vector of weights with the same length as `x`.
`sparse`	ogical indicating if the result should be sparse (of class `dgCMatrix`), using package Matrix.

Computes a contrast matrix similar to contr.sum. The reference category is however weighted by the sum of weights of the other categories.

A matrix with nlevels(x) rows and nlevels(x)- 1 columns.

Reto Buergin

1
2
3

x <- factor(rep(LETTERS[1:3], c(10, 20, 30)))
contr.wsum(x) # standard call
contr.wsum(x, sparse = TRUE) # using a sparse matrix

vcrpart documentation built on April 19, 2021, 1:07 a.m.

vcrpart index

Note that we can't provide technical support on individual packages. You should contact the package authors for that.

Description