Measuring the Power of Hierarchical Cluster Analysis
作者:
FrankB. Baker,
LawrenceJ. Hubert,
期刊:
Journal of the American Statistical Association
(Taylor Available online 1975)
卷期:
Volume 70,
issue 349
页码: 31-38
ISSN:0162-1459
年代: 1975
DOI:10.1080/01621459.1975.10480256
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
The concept of power for monotone invariant clustering procedures is developed via the possible partitions of objects at each iteration level in the obtained hierarchy. At a given level, the probability of rejecting the randomness hypothesis is obtained empirically for the possible types of partitions of thenobjects employed. The results indicate that the power of a particular hierarchical clustering procedure is a function of the type of partition. The additional problem of estimating a “true” partition at a certain level of a hierarchy is discussed briefly.
点击下载:
PDF (765KB)
返 回