Content deleted Content added
Tag: Reverted |
m Reverted edits by 115.247.40.254 (talk) (HG) (3.4.12) |
||
Line 125:
One can always decide to stop clustering when there is a sufficiently small number of clusters (number criterion). Some linkages may also guarantee that agglomeration occurs at a greater distance between clusters than the previous agglomeration, and then one can stop clustering when the clusters are too far apart to be merged (distance criterion). However, this is not the case of, e.g., the centroid linkage where the so-called reversals<ref>{{cite book |first1=P. |last1=Legendre |first2=L.F.J. |last2=Legendre |chapter=Cluster Analysis §8.6 Reversals |title=Numerical Ecology |chapter-url=https://books.google.com/books?id=DKlUIQcHhOsC&pg=PA376 |date=2012 |publisher=Elsevier |isbn=978-0-444-53868-0 |pages=376–7 |edition=3rd |series=Developments in Environmental Modelling |volume=24}}</ref> (inversions, departures from ultrametricity) may occur.
==
The basic principle of divisive clustering was published as the DIANA (DIvisive ANAlysis clustering) algorithm.<ref>{{cite book |first1=L. |last1=Kaufman |first2=P.J. |last2=Rousseeuw |chapter=6. Divisive Analysis (Program DIANA) |title=Finding Groups in Data: An Introduction to Cluster Analysis |chapter-url=https://books.google.com/books?id=YeFQHiikNo0C&pg=PA253 |orig-year=1990 |date=2009 |publisher=Wiley |isbn=978-0-470-31748-8 |pages=253–279}}</ref> Initially, all data is in the same cluster, and the largest cluster is split until every object is separate.
| |||