Matrix (version 1.0-4)

sparse.model.matrix: Construct Sparse Design / Model Matrices

Description

Construct a Model or Design Matrix

Usage

sparse.model.matrix(object, data = environment(object),
                    contrasts.arg = NULL, xlev = NULL, transpose = FALSE,
                    drop.unused.levels = FALSE, row.names=TRUE, ...)

Arguments

object

an object of an appropriate class. For the default method, a model formula or terms object.

data

a data frame created with model.frame. If another sort of object, model.frame is called first.

contrasts.arg

A list, whose entries are contrasts suitable for input to the contrasts replacement function and whose names are the names of columns of data containing

xlev

to be used as argument of model.frame if data has no "terms" attribute.

transpose

logical indicating if the transpose should be returned; if the transposed is used anyway, setting transpose = TRUE is more efficient.

drop.unused.levels

should factors have unused levels dropped? (This used to be true, implicitly in versions of Matrix up to July 2010; the default has been changed for compatibility with R's standard (dense)

row.names

logical indicating if row names should be used.

...

further arguments passed to or from other methods.

Value

• a sparse matrix extending CsparseMatrix.

  Note that model.Matrix(*, sparse=TRUE) from package MatrixModels may be often be preferable to sparse.model.matrix() nowadays, as model.Matrix() returns modelMatrix objects with additional slots assign and contrasts which relate back to the variables used. As model.Matrix() used to be part of the Matrix package for a few months in summer 2010, it is currently provided as a stub which loads the MatrixModels package and uses its model.Matrix.

See Also

model.matrix in standard R's package stats. model.Matrix which calls sparse.model.matrix or model.matrix depending on its sparse argument may be preferred to sparse.model.matrix.

as(f, "sparseMatrix") (see coerce(from = "factor", ..) in the class doc sparseMatrix) produces the transposed sparse model matrix for a single factor f (and no contrasts).

Examples

dd <- data.frame(a = gl(3,4), b = gl(4,1,12))# balanced 2-way
options("contrasts") # the default:  "contr.treatment"
sparse.model.matrix(~ a + b, dd)
sparse.model.matrix(~ -1+ a + b, dd)# no intercept --> even sparser
sparse.model.matrix(~ a + b, dd, contrasts = list(a="contr.sum"))
sparse.model.matrix(~ a + b, dd, contrasts = list(b="contr.SAS"))

## Sparse method is equivalent to the traditional one :
stopifnot(all(sparse.model.matrix(~ a + b, dd) ==
	      Matrix(model.matrix(~ a + b, dd), sparse=TRUE)),
          all(sparse.model.matrix(~ 0+ a + b, dd) ==
	      Matrix(model.matrix(~ 0+ a + b, dd), sparse=TRUE)))