Inference for transition probabilities in non-Markov multi-state models

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Inference for transition probabilities in non-Markov multi-state models. / Andersen, Per Kragh; Wandall, Eva Nina Sparre; Pohar Perme, Maja.

I: Lifetime Data Analysis, Bind 28, 2022, s. 585–604.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Andersen, PK, Wandall, ENS & Pohar Perme, M 2022, 'Inference for transition probabilities in non-Markov multi-state models', Lifetime Data Analysis, bind 28, s. 585–604. https://doi.org/10.1007/s10985-022-09560-w

APA

Andersen, P. K., Wandall, E. N. S., & Pohar Perme, M. (2022). Inference for transition probabilities in non-Markov multi-state models. Lifetime Data Analysis, 28, 585–604. https://doi.org/10.1007/s10985-022-09560-w

Vancouver

Andersen PK, Wandall ENS, Pohar Perme M. Inference for transition probabilities in non-Markov multi-state models. Lifetime Data Analysis. 2022;28:585–604. https://doi.org/10.1007/s10985-022-09560-w

Author

Andersen, Per Kragh ; Wandall, Eva Nina Sparre ; Pohar Perme, Maja. / Inference for transition probabilities in non-Markov multi-state models. I: Lifetime Data Analysis. 2022 ; Bind 28. s. 585–604.

Bibtex

@article{0407b00e6bc54fe59818269860b82abb,

title = "Inference for transition probabilities in non-Markov multi-state models",

abstract = "Multi-state models are frequently used when data come from subjects observed over time and where focus is on the occurrence of events that the subjects may experience. A convenient modeling assumption is that the multi-state stochastic process is Markovian, in which case a number of methods are available when doing inference for both transition intensities and transition probabilities. The Markov assumption, however, is quite strict and may not fit actual data in a satisfactory way. Therefore, inference methods for non-Markov models are needed. In this paper, we review methods for estimating transition probabilities in such models and suggest ways of doing regression analysis based on pseudo observations. In particular, we will compare methods using land-marking with methods using plug-in. The methods are illustrated using simulations and practical examples from medical research.",

keywords = "Land-marking, Markov process, Multi-state model, Non-Markov model, Plug-in, Pseudo observations, State occupation probability, Survival analysis, Transition intensity, Transition probability",

author = "Andersen, {Per Kragh} and Wandall, {Eva Nina Sparre} and {Pohar Perme}, Maja",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.",

year = "2022",

doi = "10.1007/s10985-022-09560-w",

language = "English",

volume = "28",

pages = "585–604",

journal = "Lifetime Data Analysis",

issn = "1380-7870",

publisher = "Springer",

}

RIS

TY - JOUR

T1 - Inference for transition probabilities in non-Markov multi-state models

AU - Andersen, Per Kragh

AU - Wandall, Eva Nina Sparre

AU - Pohar Perme, Maja

PY - 2022

Y1 - 2022

N2 - Multi-state models are frequently used when data come from subjects observed over time and where focus is on the occurrence of events that the subjects may experience. A convenient modeling assumption is that the multi-state stochastic process is Markovian, in which case a number of methods are available when doing inference for both transition intensities and transition probabilities. The Markov assumption, however, is quite strict and may not fit actual data in a satisfactory way. Therefore, inference methods for non-Markov models are needed. In this paper, we review methods for estimating transition probabilities in such models and suggest ways of doing regression analysis based on pseudo observations. In particular, we will compare methods using land-marking with methods using plug-in. The methods are illustrated using simulations and practical examples from medical research.

AB - Multi-state models are frequently used when data come from subjects observed over time and where focus is on the occurrence of events that the subjects may experience. A convenient modeling assumption is that the multi-state stochastic process is Markovian, in which case a number of methods are available when doing inference for both transition intensities and transition probabilities. The Markov assumption, however, is quite strict and may not fit actual data in a satisfactory way. Therefore, inference methods for non-Markov models are needed. In this paper, we review methods for estimating transition probabilities in such models and suggest ways of doing regression analysis based on pseudo observations. In particular, we will compare methods using land-marking with methods using plug-in. The methods are illustrated using simulations and practical examples from medical research.

KW - Land-marking

KW - Markov process

KW - Multi-state model

KW - Non-Markov model

KW - Plug-in

KW - Pseudo observations

KW - State occupation probability

KW - Survival analysis

KW - Transition intensity

KW - Transition probability

U2 - 10.1007/s10985-022-09560-w

DO - 10.1007/s10985-022-09560-w

M3 - Journal article

C2 - 35764854

AN - SCOPUS:85132985805

VL - 28

SP - 585

EP - 604

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

SN - 1380-7870

ER -

ID: 312472703