Selecting the Number of States in Hidden Markov Models: Pragmatic Solutions Illustrated Using Animal Movement

  • Jennifer Pohle
  • Roland Langrock
  • Floris M. van Beest
  • Niels Martin Schmidt
Article

Abstract

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.

Keywords

Animal movement Information criteria Selection bias Unsupervised learning 

Supplementary material

13253_2017_283_MOESM1_ESM.pdf (17 kb)
Supplementary material 1 (pdf 16 KB)
13253_2017_283_MOESM2_ESM.pdf (6 kb)
Supplementary material 2 (pdf 5 KB)
13253_2017_283_MOESM3_ESM.r (7 kb)
Supplementary material 3 (R 7 KB)
13253_2017_283_MOESM4_ESM.cpp (0 kb)
Supplementary material 4 (cpp 0 KB)
13253_2017_283_MOESM5_ESM.txt (1.1 mb)
Supplementary material 5 (txt 1076 KB)
13253_2017_283_MOESM6_ESM.r (3 kb)
Supplementary material 6 (R 2 KB)
13253_2017_283_MOESM7_ESM.pdf (159 kb)
Supplementary material 7 (pdf 159 KB)

References

  1. Biernacki, C., Celeux, G. & Govaert, G. (2013), Assessing a mixture model for clustering with the integrated completed likelihood IEEE Transactions on pattern analysis and machine intelligence, 22, 719–725.Google Scholar
  2. Broekhuis, F., Grünewälder, S., McNutt, J.W. & Macdonald, D.W. (2014), Optimal hunting conditions drive circalunar behavior of a diurnal carnivore. Behavioral Ecology, 25, 1285–1275.CrossRefGoogle Scholar
  3. Burnham, K.P. & Anderson, D.R. (2002), Model Selection and Multimodel Inference, Second Edition, Springer, New York.MATHGoogle Scholar
  4. Celeux, G. & Durand, J.-B. (2008), Selecting hidden Markov model state number with cross-validated likelihood. Computational Statistics, 23, 541–564.MathSciNetCrossRefMATHGoogle Scholar
  5. DeRuiter, S.L., Langrock, R., Skirbutas, T., Goldbogen, J.A., Calambokidis, J., Friedlaender, A.S. & Southall, B.L. (in press), A multivariate mixed hidden Markov model for blue whale behaviour and responses to sound exposure. Annals of Applied Statistics, 11, 362–392.Google Scholar
  6. Gneiting, T. & Raftery, A.E. (2007), Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102, 359–378.MathSciNetCrossRefMATHGoogle Scholar
  7. Hennig, C. (2015), What are the true clusters? Pattern Recognition Letters, 64, 53–62.CrossRefMATHGoogle Scholar
  8. Langrock, R. (2012), Flexible latent-state modelling of Old Faithful’s eruption inter-arrival times in 2009. Australian and New Zealand Journal of Statistics, 54, 261–279.MathSciNetCrossRefMATHGoogle Scholar
  9. Langrock, R., King, R., Matthiopoulos, J., Thomas, L., Fortin, D. & Morales, J.M. (2012), Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions. Ecology, 93, 2336–2342.CrossRefPubMedGoogle Scholar
  10. Langrock, R., Kneib, T., Sohn, A. & DeRuiter, S.L. (2015), Nonparametric inference in hidden Markov models using P-splines. Biometrics, 71, 520–528.MathSciNetCrossRefPubMedMATHGoogle Scholar
  11. Langrock, R., Marques, T.A., Baird, R.W. & Thomas, L. (2014), Modeling the diving behavior of whales: a latent-variable approach with feedback and semi-Markovian components. Journal of Agricultural, Biological and Environmental Statistics, 19, 82–100.MathSciNetCrossRefMATHGoogle Scholar
  12. Leos-Barajas, V., Photopoulou, T., Langrock, R., Patterson, T.A., Watanabe, Y.Y., Murgatroyd, M. & Papastamatiou, Y.P. (in press), Analysis of animal accelerometer data using hidden Markov models. Methods in Ecology and Evolution, 8, 161–173.Google Scholar
  13. Li, M. & Bolker, B.M. (2017), Incorporating periodic variability in hidden Markov models for animal movement Movement Ecology, 5, DOI:10.1186/s40462-016-0093-6.
  14. Michelot, T., Langrock, R. & Patterson, T.A. (2016), moveHMM: An R package for analysing animal movement data using hidden Markov models. Methods in Ecology and Evolution, 7, 1308–1315.CrossRefGoogle Scholar
  15. Morales, J.M., Haydon, D.T., Frair, J., Holsinger, K.E. & Fryxell, J.M. (2004), Extracting more out of relocation data: building movement models as mixtures of random walks. Ecology, 85, 2436–2445.CrossRefGoogle Scholar
  16. Patterson, T.A., Basson, M., Bravington, M.V. & Gunn, J.S. (2009), Classifying movement behaviour in relation to environmental conditions using hidden Markov models. Journal of Animal Ecology, 78, 1113–1123.CrossRefPubMedGoogle Scholar
  17. Patterson, T.A., Parton, A., Langrock, R., Blackwell, P.G., Thomas, L. & King, R. (2016), Statistical modelling of animal movement: a myopic review and a discussion of good practice. arXiv:1603.07511.
  18. Pradel, R. (2005), Multievent: an extension of multistate capture–recapture models to uncertain states, Biometrics, 61, 442–447.MathSciNetCrossRefPubMedMATHGoogle Scholar
  19. Robert, C.P., Rydén, T. & Titterington, D.M. (2000), Bayesian inference in hidden Markov models through the reversible jump Markov chain Monte Carlo method. Journal of the Royal Statistical Society Series B, 62, 57–75.MathSciNetCrossRefMATHGoogle Scholar
  20. Schmidt, N.M., van Beest, F.M., Mosbacher, J.B., Stelvig, M., Hansen, L.H. & C. Grøndahl. (2016), Ungulate movement in an extreme seasonal environment: Year-round movement patterns of high-arctic muskoxen. Wildlife Biology, 22, 253–267.CrossRefGoogle Scholar
  21. Schwarz, G. (1978), Estimating the dimension of a model. The Annals of Statistics, 6, 461–464.ADSMathSciNetCrossRefMATHGoogle Scholar
  22. Stone, M. (1977), An asymptotic equivalence of choice of model by cross-validation and Akaike’s Criterion. Journal of the Royal Statistical Society Series B, 39, 44–47.ADSMathSciNetMATHGoogle Scholar
  23. Towner, A., Leos-Barajas, V., Langrock, R., Schick, R.S., Smale, M.J., Jewell, O., Kaschke, T. & Papastamatiou, Y.P. (2016), Sex-specific and individual preferences for hunting strategies in white sharks. Functional Ecology, 30, 1397–1407.CrossRefGoogle Scholar
  24. Zucchini, W. (2000), An introduction to model selection. Journal of Mathematical Psychology, 44, 41–61.CrossRefPubMedMATHGoogle Scholar
  25. Zucchini, W., MacDonald, I.L. & Langrock, R. (2016), Hidden Markov Models for Time Series: An Introduction using R, Second Edition, Chapman & Hall/CRC, Boca Raton.MATHGoogle Scholar

Copyright information

© International Biometric Society 2017

Authors and Affiliations

  • Jennifer Pohle
    • 1
  • Roland Langrock
    • 1
  • Floris M. van Beest
    • 2
  • Niels Martin Schmidt
    • 2
  1. 1.Bielefeld UniversityBielefeldGermany
  2. 2.Aarhus UniversityRoskildeDenmark

Personalised recommendations