Advanced search
1 file | 378.98 KB Add to list

Two-state imprecise Markov chains for statistical modelling of two-state non-Markovian processes

Author
Organization
Abstract
This paper proposes a method for fitting a two-state imprecise Markov chain to time series data from a two-state non-Markovian process. Such non-Markovian processes are common in practical applications. We focus on how to fit modelling parameters based on data from a process where time to transition is not exponentially distributed, thereby violating the Markov assumption. We do so by first fitting a many-state (i.e. having more than two states) Markov chain to the data, through its associated phase-type distribution. Then, we lump the process to a two-state imprecise Markov chain. In practical applications, a two-state imprecise Markov chain might be more convenient than a many-state Markov chain, as we have closed analytic expressions for typical quantities of interest (including the lower and upper expectation of any function of the state at any point in time). A numerical example demonstrates how the entire inference process (fitting and prediction) can be done using Markov chain Monte Carlo, for a given set of prior distributions on the parameters. In particular, we numerically identify the set of posterior densities and posterior lower and upper expectations on all model parameters and predictive quantities. We compare our inferences under a range of sample sizes and model assumptions.

Downloads

  • troffaes19b.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 378.98 KB

Citation

Please use this url to cite or link to this publication:

MLA
Troffaes, Matthias, et al. “Two-State Imprecise Markov Chains for Statistical Modelling of Two-State Non-Markovian Processes.” Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications, edited by Jasper De Bock et al., vol. 103, PMLR, 2019, pp. 394–403.
APA
Troffaes, M., Krak, T., & Bains, H. (2019). Two-state imprecise Markov chains for statistical modelling of two-state non-Markovian processes. In J. De Bock, C. P. de Campos, G. De Cooman, E. Quaeghebeur, & G. Wheeler (Eds.), Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications (Vol. 103, pp. 394–403). Ghent, Belgium: PMLR.
Chicago author-date
Troffaes, Matthias, Thomas Krak, and Henna Bains. 2019. “Two-State Imprecise Markov Chains for Statistical Modelling of Two-State Non-Markovian Processes.” In Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications, edited by Jasper De Bock, Cassio P. de Campos, Gert De Cooman, Erik Quaeghebeur, and Gregory Wheeler, 103:394–403. Ghent, Belgium: PMLR.
Chicago author-date (all authors)
Troffaes, Matthias, Thomas Krak, and Henna Bains. 2019. “Two-State Imprecise Markov Chains for Statistical Modelling of Two-State Non-Markovian Processes.” In Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications, ed by. Jasper De Bock, Cassio P. de Campos, Gert De Cooman, Erik Quaeghebeur, and Gregory Wheeler, 103:394–403. Ghent, Belgium: PMLR.
Vancouver
1.
Troffaes M, Krak T, Bains H. Two-state imprecise Markov chains for statistical modelling of two-state non-Markovian processes. In: De Bock J, de Campos CP, De Cooman G, Quaeghebeur E, Wheeler G, editors. Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications. Ghent, Belgium: PMLR; 2019. p. 394–403.
IEEE
[1]
M. Troffaes, T. Krak, and H. Bains, “Two-state imprecise Markov chains for statistical modelling of two-state non-Markovian processes,” in Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications, Ghent, Belgium, 2019, vol. 103, pp. 394–403.
@inproceedings{8627474,
  abstract     = {This paper proposes a method for fitting a two-state imprecise Markov chain to time series data from a two-state non-Markovian process. Such non-Markovian processes are common in practical applications. We focus on how to fit modelling parameters based on data from a process where time to transition is not exponentially distributed, thereby violating the Markov assumption. We do so by first fitting a many-state (i.e. having more than two states) Markov chain to the data, through its associated phase-type distribution. Then, we lump the process to a two-state imprecise Markov chain. In practical applications, a two-state imprecise Markov chain might be more convenient than a many-state Markov chain, as we have closed analytic expressions for typical quantities of interest (including the lower and upper expectation of any function of the state at any point in time). A numerical example demonstrates how the entire inference process (fitting and prediction) can be done using Markov chain Monte Carlo, for a given set of prior distributions on the parameters. In particular, we numerically identify the set of posterior densities and posterior lower and upper expectations on all model parameters and predictive quantities. We compare our inferences under a range of sample sizes and model assumptions.},
  author       = {Troffaes, Matthias and Krak, Thomas and Bains, Henna},
  booktitle    = {Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications},
  editor       = {De Bock, Jasper and de Campos, Cassio P. and De Cooman, Gert and Quaeghebeur, Erik and Wheeler, Gregory},
  issn         = {2640-3498},
  language     = {eng},
  location     = {Ghent, Belgium},
  pages        = {394--403},
  publisher    = {PMLR},
  title        = {Two-state imprecise Markov chains for statistical modelling of two-state non-Markovian processes},
  volume       = {103},
  year         = {2019},
}