cmds: Classical (Metric) Multidimensional Scaling

In mkampert/rCOSA: Clustering Objects on Subsets of Attributes (COSA)

Description

Classical metric multidimensional scaling which is the same as the cmdscale in the stats package. Which follows the analyis of Mardia (1978)

Usage

cmds(
  D,
  groupnr = NULL,
  main = NULL,
  colv = palette()[c(8, 2, 4, 3, 5, 6, 7, 1)],
  PLOT = TRUE,
  ...
)

Arguments

D	dissimilarities/distances of class dist.
groupnr	groupnr when known, each object can be given a number to which group it belongs
main	title of the plot, by default there is no title.
colv	vector containing color names for each group number
PLOT	whether to plot or not to plot, by default TRUE.
...	arguments that can be parsed to cmdscale procedures.

Value

similar output as cmdscale

References

Mardia, K.V. (1978). Some properties of classical multidimensional scaling. Communications on Statistics - Theory and Methods, A7, 1233-41.
doi: https://doi.org/10.1080/03610927808827707

mkampert/rCOSA documentation built on Dec. 23, 2019, 8:21 p.m.