seriation: uniscale – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

uniscale

Unidimensional Scaling from Seriation Results

Description

Performs (approximate) unidimensional scaling by first performin seriation to obtain a permutation and the using the permutation to calulate the configuration.

Usage

uniscale(d, order = NULL, method = "QAP_LS", rep = 10, ...)

Arguments

`d`	a dissimilarity matrix.
`order`	a precomputed permutation (configuration) order. If `NULL`, then seriation is performed using the method specified in `method`.
`method`	seriation method used if `o` is `NULL`.
`rep`	Number of repetitions of the seriation heuristic.
`...`	additional arguments are passed on to the seriation method.

Details

Uses the method describes in Maier and De Leeuw (2015) to calculate the minimum stress configuration for either a given configuration/permutation/order or for a permutation computed via a seriation method.

The code is similar to uniscale in smacof, but scales to larger datasets since it does not check all permutations.

Value

A vector with the fitted configuration.

Author(s)

Michael Hahsler with code from Patrick Mair (from smacof).

References

Mair P., De Leeuw J. (2015). Unidimensional scaling. In Wiley StatsRef: Statistics Reference Online, Wiley, New York. doi: 10.1002/9781118445112.stat06462.pub2

Examples

data(SupremeCourt)

d <- as.dist(SupremeCourt)

sc <- uniscale(d)
sc

orderplot(sc)

seriation

Infrastructure for Ordering Objects Using Seriation

v1.2-9

GPL-3

Authors

Michael Hahsler [aut, cre, cph], Christian Buchta [aut, cph], Kurt Hornik [aut, cph], Fionn Murtagh [ctb, cph], Michael Brusco [ctb, cph], Stephanie Stahl [ctb, cph], Hans-Friedrich Koehn [ctb, cph]

Initial release

2020-09-29