We propose a random cluster generation algorithm that has the desired features: (1) the population degree of separation between clusters and the nearest neighboring clusters can be set to a specified value, based on a separation index; (2) no constraint is imposed on the isolation among clusters in each dimension; (3) the covariance matrices correspond to different shapes, diameters and orientations; (4) the full cluster structures generally could not be detected simply from pair-wise scatterplots of variables; (5) noisy variables and outliers can be imposed to make the cluster structures harder to be recovered. This algorithm is an improvement on the method used in Milligan (1985).
%0 Journal Article
%1 qiu_generation_2006
%A Qiu, Weiliang
%A Joe, Harry
%D 2006
%J Journal of Classification
%K Sampler bioinformatics, clustering, correlations, covariance matrix,
%N 2
%P 315--334
%R 10.1007/s00357-006-0018-y
%T Generation of random clusters with specified degree of separation
%U http://0-link.springer.com.prospero.murdoch.edu.au/article/10.1007/s00357-006-0018-y
%V 23
%X We propose a random cluster generation algorithm that has the desired features: (1) the population degree of separation between clusters and the nearest neighboring clusters can be set to a specified value, based on a separation index; (2) no constraint is imposed on the isolation among clusters in each dimension; (3) the covariance matrices correspond to different shapes, diameters and orientations; (4) the full cluster structures generally could not be detected simply from pair-wise scatterplots of variables; (5) noisy variables and outliers can be imposed to make the cluster structures harder to be recovered. This algorithm is an improvement on the method used in Milligan (1985).
@article{qiu_generation_2006,
abstract = {We propose a random cluster generation algorithm that has the desired features: (1) the population degree of separation between clusters and the nearest neighboring clusters can be set to a specified value, based on a separation index; (2) no constraint is imposed on the isolation among clusters in each dimension; (3) the covariance matrices correspond to different shapes, diameters and orientations; (4) the full cluster structures generally could not be detected simply from pair-wise scatterplots of variables; (5) noisy variables and outliers can be imposed to make the cluster structures harder to be recovered. This algorithm is an improvement on the method used in Milligan (1985).},
added-at = {2017-01-09T13:57:26.000+0100},
author = {Qiu, Weiliang and Joe, Harry},
biburl = {https://www.bibsonomy.org/bibtex/283276b3ad2a1133a635bfd8dbdc8363f/yourwelcome},
doi = {10.1007/s00357-006-0018-y},
interhash = {5c109fa6c600557dec0ff97ce9943394},
intrahash = {83276b3ad2a1133a635bfd8dbdc8363f},
issn = {0176-4268, 1432-1343},
journal = {Journal of Classification},
keywords = {Sampler bioinformatics, clustering, correlations, covariance matrix,},
language = {en},
month = sep,
number = 2,
pages = {315--334},
timestamp = {2017-01-09T14:01:11.000+0100},
title = {Generation of random clusters with specified degree of separation},
url = {http://0-link.springer.com.prospero.murdoch.edu.au/article/10.1007/s00357-006-0018-y},
urldate = {2013-07-23},
volume = 23,
year = 2006
}