Semi‐Markov Multistate Modeling Approaches for Multicohort Event History Data
Biometrical Journal · 2025-06 · 67 (3)
DOI: 10.1002/bimj.70051 ↗Kurz gefasst
Fallbericht in der Zeitschrift Biometrical Journal, online erschienen am 08.05.2025. Verfasst von Xavier Piulachs und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics and Operations Research, Polytechnic University of Catalonia, Barcelona, Spain. Hauptthemen laut MEDLINE: Markov Chains, Biometry, Models, Statistical. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Spanish Ministry of Science and Innovation, Catalan Department of Research and Universities, Ministerio de Ciencia e Innovación.
Abstract (Originalsprache)
Two Cox‐based multistate modeling approaches are compared for modeling a complex multicohort event history process. The first approach incorporates cohort information as a fixed covariate, thereby providing a direct estimation of the cohort‐specific effects. The second approach includes the cohort as a stratum variable, which offers an extra flexibility in estimating the transition probabilities. Additionally, both approaches may include possible interaction terms between the cohort and a given prognostic predictor. Furthermore, the Markov property conditional on observed prognostic covariates is assessed using a global score test. Whenever departures from the Markovian assumption are revealed for a given transition, the time of entry into the current state is incorporated as a fixed covariate, yielding a semi‐Markov process. The two proposed methods are applied to a three‐wave dataset of COVID‐19‐hospitalized adults in the southern Barcelona metropolitan area (Spain), and the corresponding performance is discussed. While both semi‐Markovian approaches are shown to be useful, the preferred one will depend on the focus of the inference. To summarize, the cohort–covariate approach enables an insightful discussion on the behavior of the cohort effects, whereas the stratum–cohort approach provides flexibility to estimate transition‐specific underlying risks according to the different cohorts.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Statistics and Operations Research, Polytechnic University of Catalonia, Barcelona, Spain.
- Department of Genetics, Microbiology and Statistics, University of Barcelona, Barcelona, Spain.
- Bellvitge Biomedical Research Institute, Bellvitge University Hospital, L'Hospitalet de Llobregat, Barcelona, Spain.
- Department of Infectious Diseases, Bellvitge University Hospital, L'Hospitalet de Llobregat, Barcelona, Spain.
- Center for Biomedical Research in Infectious Diseases (CIBERINFEC), Madrid, Spain.
ORCID-Profile: Xavier Piulachs, Klaus Langohr, Mireia Besalú, Natàlia Pallarès, Jordi Carratalà, Cristian Tebé, Guadalupe Gómez Melis
Förderung
- Spanish Ministry of Science and Innovation
- Catalan Department of Research and Universities
- Ministerio de Ciencia e Innovación
Zitieren
APA
Piulachs, X., Langohr, K., Besalú, M., Pallarès, N., Carratalà, J., Tebé, C., & Melis, G. G. (2025). Semi‐Markov Multistate Modeling Approaches for Multicohort Event History Data. Biometrical Journal, 67(3). https://doi.org/10.1002/bimj.70051
Vancouver
Piulachs X, Langohr K, Besalú M, Pallarès N, Carratalà J, Tebé C, et al. Semi‐Markov Multistate Modeling Approaches for Multicohort Event History Data. Biometrical Journal. 2025;67(3). doi:10.1002/bimj.70051
BibTeX
@article{Piulachs2025,
author = {Piulachs, Xavier and Langohr, Klaus and Besalú, Mireia and Pallarès, Natàlia and Carratalà, Jordi and Tebé, Cristian and Melis, Guadalupe Gómez},
title = {Semi‐Markov Multistate Modeling Approaches for Multicohort Event History Data},
journal = {Biometrical Journal},
year = {2025},
volume = {67},
number = {3},
doi = {10.1002/bimj.70051}
}
EUVIMED