Random start forward searches with envelopes for detecting clusters in multivariate data
Data Analysis, Classification and the Forward Search: Proceedings of the …, 2006•Springer
During a forward search the plot of minimum Mahalanobis distances of observations not in
the subset provides a test for outliers. However, if clusters are present in the data, their
simple identification requires that there arc searches that initially include a preponderance of
observations from each of the unknown clusters. We use random starts to provide such
searches, combined with simulation envelopes for precise inference about clustering.
the subset provides a test for outliers. However, if clusters are present in the data, their
simple identification requires that there arc searches that initially include a preponderance of
observations from each of the unknown clusters. We use random starts to provide such
searches, combined with simulation envelopes for precise inference about clustering.
Abstract
During a forward search the plot of minimum Mahalanobis distances of observations not in the subset provides a test for outliers. However, if clusters are present in the data, their simple identification requires that there arc searches that initially include a preponderance of observations from each of the unknown clusters. We use random starts to provide such searches, combined with simulation envelopes for precise inference about clustering.
Springer
以上显示的是最相近的搜索结果。 查看全部搜索结果