Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement
We discuss the notorious problem of order selection in hidden Markov models, that is of selecting an adequate number of states, highlighting typical pitfalls and practical challenges arising when analyzing real data. Extensive simulations are used to demonstrate the reasons that render order selecti...
Published in: | Journal of Agricultural, Biological and Environmental Statistics |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | https://pure.au.dk/portal/en/publications/0a38b759-c71a-4c3e-926d-14cf9f690d19 https://doi.org/10.1007/s13253-017-0283-8 |
id |
ftuniaarhuspubl:oai:pure.atira.dk:publications/0a38b759-c71a-4c3e-926d-14cf9f690d19 |
---|---|
record_format |
openpolar |
spelling |
ftuniaarhuspubl:oai:pure.atira.dk:publications/0a38b759-c71a-4c3e-926d-14cf9f690d19 2024-02-11T10:05:52+01:00 Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement Langrock, Roland Pohle, Jennifer van Beest, Floris Schmidt, Niels Martin 2017 https://pure.au.dk/portal/en/publications/0a38b759-c71a-4c3e-926d-14cf9f690d19 https://doi.org/10.1007/s13253-017-0283-8 eng eng https://pure.au.dk/portal/en/publications/0a38b759-c71a-4c3e-926d-14cf9f690d19 info:eu-repo/semantics/closedAccess Langrock , R , Pohle , J , van Beest , F & Schmidt , N M 2017 , ' Selecting the number of states in Hidden Markov Models : Pragmatic solutions illustrated using animal movement ' , Journal of Agricultural, Biological, and Environmental Statistics , vol. 22 , no. 3 , pp. 270-293 . https://doi.org/10.1007/s13253-017-0283-8 Animal movement Information criteria Selection bias Unsupervised learning article 2017 ftuniaarhuspubl https://doi.org/10.1007/s13253-017-0283-8 2024-01-17T23:59:42Z We discuss the notorious problem of order selection in hidden Markov models, that is of selecting an adequate number of states, highlighting typical pitfalls and practical challenges arising when analyzing real data. Extensive simulations are used to demonstrate the reasons that render order selection particularly challenging in practice despite the conceptual simplicity of the task. In particular, we demonstrate why well-established formal procedures for model selection, such as those based on standard information criteria, tend to favor models with numbers of states that are undesirably large in situations where states shall be meaningful entities. We also offer a pragmatic step-by-step approach together with comprehensive advice for how practitioners can implement order selection. Our proposed strategy is illustrated with a real-data case study on muskox movement. Supplementary materials accompanying this paper appear online. Article in Journal/Newspaper muskox Aarhus University: Research Journal of Agricultural, Biological and Environmental Statistics 22 3 270 293 |
institution |
Open Polar |
collection |
Aarhus University: Research |
op_collection_id |
ftuniaarhuspubl |
language |
English |
topic |
Animal movement Information criteria Selection bias Unsupervised learning |
spellingShingle |
Animal movement Information criteria Selection bias Unsupervised learning Langrock, Roland Pohle, Jennifer van Beest, Floris Schmidt, Niels Martin Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement |
topic_facet |
Animal movement Information criteria Selection bias Unsupervised learning |
description |
We discuss the notorious problem of order selection in hidden Markov models, that is of selecting an adequate number of states, highlighting typical pitfalls and practical challenges arising when analyzing real data. Extensive simulations are used to demonstrate the reasons that render order selection particularly challenging in practice despite the conceptual simplicity of the task. In particular, we demonstrate why well-established formal procedures for model selection, such as those based on standard information criteria, tend to favor models with numbers of states that are undesirably large in situations where states shall be meaningful entities. We also offer a pragmatic step-by-step approach together with comprehensive advice for how practitioners can implement order selection. Our proposed strategy is illustrated with a real-data case study on muskox movement. Supplementary materials accompanying this paper appear online. |
format |
Article in Journal/Newspaper |
author |
Langrock, Roland Pohle, Jennifer van Beest, Floris Schmidt, Niels Martin |
author_facet |
Langrock, Roland Pohle, Jennifer van Beest, Floris Schmidt, Niels Martin |
author_sort |
Langrock, Roland |
title |
Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement |
title_short |
Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement |
title_full |
Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement |
title_fullStr |
Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement |
title_full_unstemmed |
Selecting the number of states in Hidden Markov Models:Pragmatic solutions illustrated using animal movement |
title_sort |
selecting the number of states in hidden markov models:pragmatic solutions illustrated using animal movement |
publishDate |
2017 |
url |
https://pure.au.dk/portal/en/publications/0a38b759-c71a-4c3e-926d-14cf9f690d19 https://doi.org/10.1007/s13253-017-0283-8 |
genre |
muskox |
genre_facet |
muskox |
op_source |
Langrock , R , Pohle , J , van Beest , F & Schmidt , N M 2017 , ' Selecting the number of states in Hidden Markov Models : Pragmatic solutions illustrated using animal movement ' , Journal of Agricultural, Biological, and Environmental Statistics , vol. 22 , no. 3 , pp. 270-293 . https://doi.org/10.1007/s13253-017-0283-8 |
op_relation |
https://pure.au.dk/portal/en/publications/0a38b759-c71a-4c3e-926d-14cf9f690d19 |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/10.1007/s13253-017-0283-8 |
container_title |
Journal of Agricultural, Biological and Environmental Statistics |
container_volume |
22 |
container_issue |
3 |
container_start_page |
270 |
op_container_end_page |
293 |
_version_ |
1790603087067480064 |