EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advanced Posterior Analyses of Hidden Markov Models: Finite Markov Chain Imbedding and Hybrid Decoding

Zenia Elise Damgaard Bæk, Moisès Coll Macià, Laurits Skov, Asger Hobolth

Scandinavian Journal of Statistics · 2026-12 · 53 (4) · 1413-1431

DOI: 10.1111/sjos.70088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scandinavian Journal of Statistics, online erschienen am 28.07.2026. Verfasst von Zenia Elise Damgaard Bæk und 3 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Novo Nordisk Fonden, Danish Data Science Academy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Two major tasks in applications of hidden Markov models are to (i) compute distributions of summary statistics of the hidden state sequence, and (ii) decode the hidden state sequence. We describe finite Markov chain imbedding (FMCI) and hybrid decoding to solve each of these two tasks. In the first part of our paper, we use FMCI to compute posterior distributions of summary statistics such as the number of visits to a hidden state, the total time spent in a hidden state, the sojourn time in a hidden state, and the longest run length. We use samples generated from the posterior distribution of the hidden state sequence, conditional on the observed sequence, to establish the FMCI framework. In the second part of our paper, we apply hybrid segmentation for improved decoding of an HMM. We demonstrate that hybrid decoding shows increased performance compared to Viterbi or Posterior decoding (often also referred to as global or local decoding), and we introduce a novel procedure for choosing the tuning parameter in the hybrid procedure. Furthermore, we provide an alternative derivation of the hybrid loss function based on weighted geometric means. We demonstrate and apply FMCI and hybrid decoding on various classical data sets and supply accompanying code for reproducibility.

Förderung

  • Novo Nordisk Fonden
  • Danish Data Science Academy

Zitieren

APA

Bæk, Z. E. D., Macià, M. C., Skov, L., & Hobolth, A. (2026). Advanced Posterior Analyses of Hidden Markov Models: Finite Markov Chain Imbedding and Hybrid Decoding. Scandinavian Journal of Statistics, 53(4), 1413-1431. https://doi.org/10.1111/sjos.70088

Vancouver

Bæk ZED, Macià MC, Skov L, Hobolth A. Advanced Posterior Analyses of Hidden Markov Models: Finite Markov Chain Imbedding and Hybrid Decoding. Scandinavian Journal of Statistics. 2026;53(4):1413-1431. doi:10.1111/sjos.70088

BibTeX
@article{Bk2026,
  author = {Bæk, Zenia Elise Damgaard and Macià, Moisès Coll and Skov, Laurits and Hobolth, Asger},
  title = {Advanced Posterior Analyses of Hidden Markov Models: Finite Markov Chain Imbedding and Hybrid Decoding},
  journal = {Scandinavian Journal of Statistics},
  year = {2026},
  volume = {53},
  number = {4},
  pages = {1413--1431},
  doi = {10.1111/sjos.70088}
}
Kostenlos starten →