Clustering and isolation in the consensus problem for partitions (Q578812): Difference between revisions
From MaRDI portal
Created a new Item |
Changed an Item |
||
Property / review text | |||
We examine the problem of aggregating several partitions of a finite set into a single consensus partition. We note that the dual concepts of clustering and isolation are especially significant in this connection. The hypothesis that a consensus partition should respect unanimity with respect to either concept leads us to stress a consensus interval rather than a single partition. The extremes of this inverval are characterized axiomatically. If a sufficient totality of traits has been measured, and if measurement errors are independent, then a ``true'' classifying partition can be expected to lie in the consensus interval. The structure of the partitions in the interval lends itself to partial solutions of the consensus problem. Conditional entropy may be used to quantify the uncertainty inherent in the interval as a whole. | |||
Property / review text: We examine the problem of aggregating several partitions of a finite set into a single consensus partition. We note that the dual concepts of clustering and isolation are especially significant in this connection. The hypothesis that a consensus partition should respect unanimity with respect to either concept leads us to stress a consensus interval rather than a single partition. The extremes of this inverval are characterized axiomatically. If a sufficient totality of traits has been measured, and if measurement errors are independent, then a ``true'' classifying partition can be expected to lie in the consensus interval. The structure of the partitions in the interval lends itself to partial solutions of the consensus problem. Conditional entropy may be used to quantify the uncertainty inherent in the interval as a whole. / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 62H30 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 06B99 / rank | |||
Normal rank | |||
Property / zbMATH DE Number | |||
Property / zbMATH DE Number: 4013784 / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
lattice of partitions | |||
Property / zbMATH Keywords: lattice of partitions / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
consensus function | |||
Property / zbMATH Keywords: consensus function / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
consensus partition | |||
Property / zbMATH Keywords: consensus partition / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
clustering | |||
Property / zbMATH Keywords: clustering / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
isolation | |||
Property / zbMATH Keywords: isolation / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
measurement errors | |||
Property / zbMATH Keywords: measurement errors / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
consensus interval | |||
Property / zbMATH Keywords: consensus interval / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
Conditional entropy | |||
Property / zbMATH Keywords: Conditional entropy / rank | |||
Normal rank |
Revision as of 18:17, 1 July 2023
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Clustering and isolation in the consensus problem for partitions |
scientific article |
Statements
Clustering and isolation in the consensus problem for partitions (English)
0 references
1986
0 references
We examine the problem of aggregating several partitions of a finite set into a single consensus partition. We note that the dual concepts of clustering and isolation are especially significant in this connection. The hypothesis that a consensus partition should respect unanimity with respect to either concept leads us to stress a consensus interval rather than a single partition. The extremes of this inverval are characterized axiomatically. If a sufficient totality of traits has been measured, and if measurement errors are independent, then a ``true'' classifying partition can be expected to lie in the consensus interval. The structure of the partitions in the interval lends itself to partial solutions of the consensus problem. Conditional entropy may be used to quantify the uncertainty inherent in the interval as a whole.
0 references
lattice of partitions
0 references
consensus function
0 references
consensus partition
0 references
clustering
0 references
isolation
0 references
measurement errors
0 references
consensus interval
0 references
Conditional entropy
0 references