Classification of binary vectors by stochastic complexity.

DOI10.1006/jmva.1997.1687zbMath1090.62542MaRDI QIDQ1372217

Mats Gyllenberg, Timo Koski, Martin Verlaan

Publication date: 1997

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jmva.1997.1687

zbMATH Keywords

classification; principle of maximum entropy; maximum likelihood estimate; information content; AUTOCLASS; bacterial identification; maximal predictive classification; mixture of multivariate Bernouli distributions; universal source codes

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

62B10: Statistical aspects of information-theoretic topics

Related Items

Probabilistic Models for Bacterial Taxonomy, Bayesian predictiveness, exchangeability and sufficientness in bacterial taxonomy, A unified view on clustering binary data

Uses Software

• AutoClass

Cites Work

• An improved algorithm for finding diagnostic taxonomic descriptions
• Parameter modification for clustering criteria
• Numerical taxonomy and the principle of maximum entropy
• Clustering criteria for discrete data and latent class models
• Estimating the dimension of a model
• Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
• Information-Theoretical Aspects of Inductive and Deductive Inference
• Approximating probability distributions to reduce storage requirements
• Approximate Confidence Intervals for the Number of Clusters
• Locally optimal block quantizer design
• Maximal Predictive Classification
• Asymptotic behaviour of classification maximum likelihood estimates
• Non-uniqueness in probabilistic numerical identification of bacteria
• An Information Measure for Classification
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item