Skip to content

Research at St Andrews

Nonparametric inference in hidden Markov models using P-splines

Research output: Contribution to journalArticle

DOI

Author(s)

Roland Langrock, Thomas Kneib, Alexander Sohn, Stacy Lynn De Ruiter

School/Research organisations

Abstract

Hidden Markov models (HMMs) are flexible time series models in which the distribution of the observations depends on unobserved serially correlated states. The state-dependent distributions in HMMs are usually taken from some class of parametrically specified distributions. The choice of this class can be difficult, and an unfortunate choice can have serious consequences for example on state estimates, and more generally on the resulting model complexity and interpretation. We demonstrate these practical issues in a real data application concerned with vertical speeds of a diving beaked whale, where we demonstrate that parametric approaches can easily lead to overly complex state processes, impeding meaningful biological inference. In contrast, for the dive data, HMMs with nonparametrically estimated state-dependent distributions are much more parsimonious in terms of the number of states and easier to interpret, while fitting the data equally well. Our nonparametric estimation approach is based on the idea of representing the densities of the state-dependent distributions as linear combinations of a large number of standardized B-spline basis functions, imposing a penalty term on non-smoothness in order to maintain a good balance between goodness-of-fit and smoothness.
Close

Details

Original languageEnglish
Pages (from-to)520-528
JournalBiometrics
Volume71
Issue number2
Early online date13 Jan 2015
DOIs
Publication statusPublished - 2015

    Research areas

  • Animal movement, B-splines, Forward algorithm , Maximum likelihood, Penalized smoothing

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by journal

  1. Biometrics (Journal)

    Hannah Worthington (Reviewer)
    Apr 2018

    Activity: Publication peer-review and editorial work typesPeer review of manuscripts

  2. Biometrics (Journal)

    Hannah Worthington (Reviewer)
    Jan 2017

    Activity: Publication peer-review and editorial work typesPeer review of manuscripts

  3. Biometrics (Journal)

    Stephen Terrence Buckland (Editor)
    20052011

    Activity: Publication peer-review and editorial work typesEditor of research journal

  4. Biometrics (Journal)

    David Louis Borchers (Editor)
    2001 → …

    Activity: Publication peer-review and editorial work typesEditor of research journal

Related by journal

  1. Cluster capture-recapture to account for identification uncertainty on aerial surveys of animal populations

    Stevenson, B. C., Borchers, D. L. & Fewster, R. M., 2019, In : Biometrics. 75, 1, p. 326-336 11 p.

    Research output: Contribution to journalArticle

  2. Open population maximum likelihood spatial capture-recapture

    Glennie, R., Borchers, D. L., Murchie, M., Harmsen, B. J. & Foster, R. J., 25 Jul 2019, In : Biometrics. Early View, 11 p.

    Research output: Contribution to journalArticle

  3. Distance sampling detection functions: 2D or not 2D?

    Borchers, D. L. & Cox, M. J., 15 Jun 2017, In : Biometrics. 73, 2, p. 593-602 10 p.

    Research output: Contribution to journalArticle

  4. Double-observer line transect surveys with Markov-modulated Poisson process models for overdispersed animal availability

    Borchers, D. L. & Langrock, R., Dec 2015, In : Biometrics. 71, 4, p. 1060-1069 10 p.

    Research output: Contribution to journalArticle

ID: 54630410