bertinzscore: Standardised (studentised) matrix

In bertin: Bertin matrix display

Description

Calculate standardised matrix for Bertin analysis. Marginal means and marginal permutation, sorting by score, are cached.

Usage

bertinzscore(z, var.orientation = c("byrow", "bycolumn", "global"), trim = 0, na.rm = FALSE, ...)

Arguments

z	A data matrix
var.orientation	"byrow", "bycolumn", "global"). By default, following Bertin's conventions variables are in rows. Use var.orientation="bycolumn" for R conventions.
trim	the fraction (0 to 0.5) of observations to be trimmed from each end of x before the mean is computed. Values of trim outside that range are taken as the nearest endpoint.
na.rm	a logical value indicating whether NA values should be stripped before the computation proceeds.
...	other parameters, (see mean).

Details

Calculates (x-mean)/sd. If sd is zero, zero is returned as value.

Value

scores

An augmented matrix of rank scores. The matrix has the class "bertin" and carries the attributes: var.orientation cached. rowmeans row wise mean ranks roworder order of rows by row means colmeans column wise mean ranks colorder order of columns by column means This list is subject to change.

Note

If trim !=0, a trimmed version of sd() or a robust version should be used.

Author(s)

G. Sawitzki

See Also

bertinrank.

Examples

data(Hotel)
hotelzscores <- bertinzscore(Hotel)
plot.bertin(hotelzscores)

bertin documentation built on May 2, 2019, 5:54 p.m.