clest: Clest: A prediction-based resampling method for estimating...

In mattmail/clusterAnalysis: Several tools for determining the number of clusters in a dataset

Description

This method measures the similarity of two clustering computed on two non-overlapping subsamples of the dataset. The obtained measures are then compared with other similarity measures taken on generated datasets. Those generated datasets are computed as in the gap statistics method (Tibshirani et al, 2001).

Usage

clest(X, maxK, clusterAlg = myKmean, similarity = adj.rand.index,
  pmax = 0.05, dmin = 0.05, B = 50, B0 = 20, rho = 0.6,
  verbose = TRUE, ...)

Arguments

X	data matrix or data frame of size n x d, n observations and d features
maxK	maximum number of clusters to evaluate.
clusterAlg	clustering algorithm. Its output must be a list having a compoment "cluster" containing the assignation of each observation. For more details, check the formatting of function myKmean.
similarity	function measuring the similarity between two partitions.
pmax	threshold for the p-value
dmin	threshold for the d-value
B	number of resampling iterations
B0	number of reference datasets to generate
rho	proportion of the train/test set
verbose	logical, if TRUE, plots the evolution of the algorithm
...	additional parameters for the clustering algorithm

Value

list of 3 attributes:

p

vector of p-values

d

vector of d-values

kopt

optimal number of clusters

References

• Dudoit, S. and Fridlyand, J. (2002). A prediction-based resampling method for estimating the number of clusters in a dataset. Genome Biology, 3(7):research0036.1. https://doi.org/10.1186/gb-2002-3-7-research0036

• Tibshirani, R., Walther, G., and Hastie, T. (2001). Estimating the number of clusters in a data set via the gap statistic.Journal of the Royal Statistical Society Series B, 63:411-423.

mattmail/clusterAnalysis documentation built on Nov. 4, 2019, 6:18 p.m.