clues (version 0.6.2.2)

Vowel: The Vowel Data Set

Description

The vowel data set studied in Hastie, Tibshirani and Friedman (2001).

Usage

data(Vowel)

Value

A list consists of a 528 by 2 data matrix and a 528 by 1 cluster membership vector. There are 11 clusters each containing 48 data points in a two-dimensional space.

Details

In the original vowel data set, the 11 different words, with each one representing a vowel sound, correspond to 11 different clusters. There are 528 training observations and 462 testing observations. The training observations are employed to asset the performance of the clues algorithm in Wang et al. (2007) and refered as the Vowel data set. The 10 dimensional data was projected into a 2-dimensional space for examination purpose according to the method described in Hastie, Tibshirani and Friedman(pages 84, 92, 2001).

References

Hastie, T., Tibshirani, R., Friedman, J. (2001) The elements of statistical learning. Springer-Verlag.

Wang, S., Qiu, W., and Zamar, R. H. (2007). CLUES: A non-parametric clustering method based on local shrinking. Computational Statistics & Data Analysis, Vol. 52, issue 1, pages 286-298.

Examples

# NOT RUN {
    data(Vowel)
 
    # data matrix
    vowel <- Vowel$vowel
 
    # 'true' cluster membership
    vowel.mem <- Vowel$vowel.mem

    # scatter plots
    plotClusters(vowel, vowel.mem)

# }