diptest.multi: Diptest for discriminant coordinate projection

In fpc: Flexible Procedures for Clustering

Diptest for discriminant coordinate projection

Description

Diptest (Hartigan and Hartigan, 1985, see dip) for data projected in discriminant coordinate separating optimally two class means (see discrcoord) as suggested by Tantrum, Murua and Stuetzle (2003).

Usage

  diptest.multi(xdata,class,pvalue="uniform",M=100)

Arguments

xdata	matrix. Potentially multidimensional dataset.
class	vector of integers giving class numbers for observations.
pvalue	"uniform" or "tantrum". Defines whether the p-value is computed from a uniform null model as suggested in Hartigan and Hartigan (1985, using dip.test) or as suggested in Tantrum et al. (2003, using dipp.tantrum).
M	integer. Number of artificial datasets generated in order to estimate the p-value if pvalue="tantrum".

Value

The resulting p-value.

Author(s)

Christian Hennig [e-mail] https://www.unibo.it/sitoweb/christian.hennig/en/

References

J. A. Hartigan and P. M. Hartigan (1985) The Dip Test of Unimodality, Annals of Statistics, 13, 70-84.

Tantrum, J., Murua, A. and Stuetzle, W. (2003) Assessment and Pruning of Hierarchical Model Based Clustering, Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, Washington, D.C., 197-205.

Examples

  require(diptest)
  x <- cbind(runif(100),runif(100))
  partition <- 1+(x[,1]<0.5)
  d1 <- diptest.multi(x,partition)
  d2 <- diptest.multi(x,partition,pvalue="tantrum",M=10)

fpc documentation built on Sept. 24, 2024, 9:07 a.m.