Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal Behavior
The study of animal behavioral states inferred through hidden Markov models and similar state switching models has seen a significant increase in popularity in recent years. The ability to account for varying levels of behavioral scale has become possible through hierarchical hidden Markov models, b...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-05-01
|
| Series: | Frontiers in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fevo.2021.623731/full |
| id |
doaj-9557dd85b0ec4940bd14916a172a663f |
|---|---|
| record_format |
Article |
| spelling |
doaj-9557dd85b0ec4940bd14916a172a663f2021-05-05T04:59:25ZengFrontiers Media S.A.Frontiers in Ecology and Evolution2296-701X2021-05-01910.3389/fevo.2021.623731623731Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal BehaviorGiada Sacchi0Ben Swallow1School of Mathematics and Statistics, University of Edinburgh, Edinburgh, United KingdomSchool of Mathematics and Statistics, University of Glasgow, Glasgow, United KingdomThe study of animal behavioral states inferred through hidden Markov models and similar state switching models has seen a significant increase in popularity in recent years. The ability to account for varying levels of behavioral scale has become possible through hierarchical hidden Markov models, but additional levels lead to higher complexity and increased correlation between model components. Maximum likelihood approaches to inference using the EM algorithm and direct optimization of likelihoods are more frequently used, with Bayesian approaches being less favored due to computational demands. Given these demands, it is vital that efficient estimation algorithms are developed when Bayesian methods are preferred. We study the use of various approaches to improve convergence times and mixing in Markov chain Monte Carlo methods applied to hierarchical hidden Markov models, including parallel tempering as an inference facilitation mechanism. The method shows promise for analysing complex stochastic models with high levels of correlation between components, but our results show that it requires careful tuning in order to maximize that potential.https://www.frontiersin.org/articles/10.3389/fevo.2021.623731/fullparallel temperinganimal movementhierarchical hidden Markov modelsBayesian inferenceMCMC |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Giada Sacchi Ben Swallow |
| spellingShingle |
Giada Sacchi Ben Swallow Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal Behavior Frontiers in Ecology and Evolution parallel tempering animal movement hierarchical hidden Markov models Bayesian inference MCMC |
| author_facet |
Giada Sacchi Ben Swallow |
| author_sort |
Giada Sacchi |
| title |
Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal Behavior |
| title_short |
Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal Behavior |
| title_full |
Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal Behavior |
| title_fullStr |
Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal Behavior |
| title_full_unstemmed |
Toward Efficient Bayesian Approaches to Inference in Hierarchical Hidden Markov Models for Inferring Animal Behavior |
| title_sort |
toward efficient bayesian approaches to inference in hierarchical hidden markov models for inferring animal behavior |
| publisher |
Frontiers Media S.A. |
| series |
Frontiers in Ecology and Evolution |
| issn |
2296-701X |
| publishDate |
2021-05-01 |
| description |
The study of animal behavioral states inferred through hidden Markov models and similar state switching models has seen a significant increase in popularity in recent years. The ability to account for varying levels of behavioral scale has become possible through hierarchical hidden Markov models, but additional levels lead to higher complexity and increased correlation between model components. Maximum likelihood approaches to inference using the EM algorithm and direct optimization of likelihoods are more frequently used, with Bayesian approaches being less favored due to computational demands. Given these demands, it is vital that efficient estimation algorithms are developed when Bayesian methods are preferred. We study the use of various approaches to improve convergence times and mixing in Markov chain Monte Carlo methods applied to hierarchical hidden Markov models, including parallel tempering as an inference facilitation mechanism. The method shows promise for analysing complex stochastic models with high levels of correlation between components, but our results show that it requires careful tuning in order to maximize that potential. |
| topic |
parallel tempering animal movement hierarchical hidden Markov models Bayesian inference MCMC |
| url |
https://www.frontiersin.org/articles/10.3389/fevo.2021.623731/full |
| work_keys_str_mv |
AT giadasacchi towardefficientbayesianapproachestoinferenceinhierarchicalhiddenmarkovmodelsforinferringanimalbehavior AT benswallow towardefficientbayesianapproachestoinferenceinhierarchicalhiddenmarkovmodelsforinferringanimalbehavior |
| _version_ |
1721475614359158784 |