cmds: Classical Multidimensional Scaling

In kyoustat/DAS: Distance-bAsed Statistical methods

Description

Classical Multidimensional Scaling

Usage

cmds(x, ndim = 2)

Author(s)

Kisung You

References

\insertRef

torgerson_multidimensional_1952DAS

Examples

## use simple example of iris dataset 
data(iris) 
dat  = iris[,1:4]
dat.n = nrow(dat)
dat.p = ncol(dat)
dat  = dat + matrix(rnorm(dat.n*dat.p, sd=0.1), ncol=dat.p)
dmat = as.matrix(stats::dist(dat)) # distance matrix

## run the algorithm
iris.cmds = cmds(dmat, ndim=2)

## extract coordinates and class information
cx = iris.cmds$embed # embedded coordinates of CMDS
icol = iris[,5]      # class information

## visualize
opar = par(pty="s")
mc   = paste("CMDS with STRESS=",round(iris.cmds$stress,4),sep="")
plot(cx, col=icol,pch=19,main=mc)
par(opar)

kyoustat/DAS documentation built on Jan. 6, 2020, 7:10 a.m.