bmt {fusionclust}

Big Merge Tracker

Description

Solves an L1 relaxed univariate clustering criterion and returns a sequence of \lambda values where the clusters merge

Usage

bmt(x, alpha = 0.1, small.perturbation = 10^(-6))

Arguments

x

observation vector

alpha

merging threshold. Default is 0.1

small.perturbation

a small positive number to remove ties. Default is 10^(-6)

Details

solves a convex relaxation of the univariate clustering criterion given by equation (2) in the referenced paper and generates a sequence of cluster merges and corresponding \lambda values. See algorithm 1 in the referenced paper for more details.

Value

1. path - number of clusters on the big merge path

2. lambda.path - sequence of lambda where clusters merge

3. index - cluster index at the point where clusters merge

4. merge - merge points

5. split - split points

6. prob - merging proportion

7. boundaries - cluster boundaries

References

1. P. Radchenko, G. Mukherjee, Convex clustering via l1 fusion penalization, J. Roy. Statist, Soc. Ser. B (Statistical Methodology) (2017) doi:10.1111/rssb.12226.

See Also

nclust

Examples

library(fusionclust)
set.seed(42)
x<- c(rnorm(1000,-2,1), rnorm(1000,2,1))
out<- bmt(x)