Premium
Mixture modelling of categorical sequences with secondary components
Author(s) -
Zhu Xuwen
Publication year - 2020
Publication title -
stat
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.61
H-Index - 18
ISSN - 2049-1573
DOI - 10.1002/sta4.295
Subject(s) - categorical variable , markov chain , cluster (spacecraft) , computer science , markov model , data mining , hidden markov model , transition (genetics) , mixture model , pattern recognition (psychology) , artificial intelligence , algorithm , machine learning , chemistry , biochemistry , gene , programming language
In this paper, the forward selected first‐order Markov mixture (FSFOMM) is proposed for modelling heterogeneous categorical sequences with secondary components capable of detecting outlying sequences within each cluster. Such sequences are assumed to have different transition probabilities in certain states. The model provides an attractive and flexible tool for diagnostics of unusual behaviours and parsimonious modelling of transition probabilities. The algorithm is tested on simulated as well as real‐life datasets with promising results.