×

Scalable Bayesian inference for coupled hidden Markov and semi-Markov models. (English) Zbl 07499252

Summary: Bayesian inference for coupled hidden Markov models frequently relies on data augmentation techniques for imputation of the hidden state processes. Considerable progress has been made on developing such techniques, mainly using Markov chain Monte Carlo (MCMC) methods. However, as the dimensionality and complexity of the hidden processes increase some of these methods become inefficient, either because they produce MCMC chains with high autocorrelation or because they become computationally intractable. Motivated by this fact we developed a novel MCMC algorithm, which is a modification of the forward filtering backward sampling algorithm, that achieves a good balance between computation and mixing properties, and thus can be used to analyze models with large numbers of hidden chains. Even though our approach is developed under the assumption of a Markovian model, we show how this assumption can be relaxed leading to minor modifications in the algorithm. Our approach is particularly well suited to epidemic models, where the hidden Markov chains represent the infection status of an individual through time. The performance of our method is assessed on simulated data on epidemic models for the spread of Escherichia coli O157:H7 in cattle. Supplementary materials for this article are available online.

MSC:

62-XX Statistics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Anderson, R. M.; May, R. M., Infectious Diseases of Humans: Dynamics and Control (1991), Oxford: Oxford University Press, Oxford
[2] Barbour, A. D., “Networks of Queues and the Method of Stages,”, Advances in Applied Probability, 8, 584-591 (1976) · Zbl 0342.60065 · doi:10.2307/1426145
[3] Brand, M., Coupled Hidden Markov Models for Modeling Interacting Processes (1997)
[4] Brand, M.; Oliver, N.; Pentland, A., Coupled Hidden Markov Models for Complex Action Recognition, 994-999 (1997)
[5] Carter, C. K.; Kohn, R., “On Gibbs Sampling for State Space Models,”, Biometrika, 81, 541-553 (1994) · Zbl 0809.62087 · doi:10.1093/biomet/81.3.541
[6] Chib, S., “Calculating Posterior Distributions and Modal Estimates in Markov Mixture Models,”, Journal of Econometrics, 75, 79-97 (1996) · Zbl 0864.62010 · doi:10.1016/0304-4076(95)01770-4
[7] Chimisov, C.; Łatuszyński, K.; Roberts, G. O., Adapting the Gibbs Sampler, arXiv no. 1801.09299 (2018)
[8] Cobbold, R. N.; Hancock, D. D.; Rice, D. H.; Berg, J.; Stilborn, R.; Hovde, C. J.; Besser, T. E., “Rectoanal Junction Colonization of Feedlot Cattle by Escherichia coli O157:H7 and Its Association With Supershedders and Excretion Dynamics,”, Applied and Environmental Microbiology, 73, 1563-1568 (2007) · doi:10.1128/AEM.01742-06
[9] Dong, W.; Pentland, A.; Heller, K. A., Graph-Coupled HMMs for Modeling the Spread of Infection, 227-236 (2012)
[10] Fintzi, J.; Cui, X.; Wakefield, J.; Minin, V. N., “Efficient Data Augmentation for Fitting Stochastic Epidemic Models to Prevalence Data,”, Journal of Computational and Graphical Statistics, 26, 918-929 (2017) · doi:10.1080/10618600.2017.1328365
[11] Gibson, G. J.; Renshaw, E., “Estimating Parameters in Stochastic Compartmental Models Using Markov Chain Methods,”, Mathematical Medicine and Biology, 15, 19-40 (1998) · Zbl 0916.92024 · doi:10.1093/imammb/15.1.19
[12] Łatuszyński, K.; Roberts, G. O.; Rosenthal, J. S., “Adaptive Gibbs Samplers and Related MCMC Methods,”, The Annals of Applied Probability, 23, 66-98 (2013) · Zbl 1263.60067 · doi:10.1214/11-AAP806
[13] Microsoft Corporation; Weston, S., foreach: Provides Foreach Looping Construct for R,”, R Package Version 1.4.4 (2017)
[14] Microsoft Corporation; Weston, S., “doParallel: Foreach Parallel Adaptor for the ‘Parallel’ Package,”, R Package Version 1.0.14 (2018)
[15] Neal, R. M.; Brooks, S.; Gelman, A.; Jones, G. L.; Meng, X., Handbook of Markov Chain Mote Carlo, MCMC Using Hamiltonian Dynamics, 113-162 (2011), Boca Raton, FL: Chapman & Hall/CRC, Boca Raton, FL · Zbl 1229.65018
[16] Neuts, M. F.; Teugels, J., Liber amicorum Professor Emeritus Dr. H. Florin, “Phase-Type Probability Distributions, 173-206 (1975), Leuven, Belgium: Katholieke Universiteit Leuven, Departement Wiskunde, Leuven, Belgium
[17] O’Neill, P. D.; Roberts, G. O., “Bayesian Inference for Partially Observed Stochastic Epidemics,”, Journal of the Royal Statistical Society, Series A, 162, 121-129 (1999) · doi:10.1111/1467-985X.00125
[18] R Core Team, R: A Language and Environment for Statistical Computing (2016), Vienna, Austria: R Foundation for Statistical Computing, Vienna, Austria
[19] Saul, L. K.; Jordan, M. I., Mixed Memory Markov Models: Decomposing Complex Stochastic Processes as Mixtures of Simpler Ones, Machine Learning, 37, 75-87 (1999) · Zbl 0948.68096
[20] Scott, S. L., “Bayesian Methods for Hidden Markov Models: Recursive Computing in the 21st Century,”, Journal of the American Statistical Association, 97, 337-351 (2002) · Zbl 1073.65503 · doi:10.1198/016214502753479464
[21] Sherlock, C.; Xifara, T.; Telfer, S.; Begon, M., “A Coupled Hidden Markov Model for Disease Interactions,”, Journal of the Royal Statistical Society, Series C, 62, 609-627 (2013) · doi:10.1111/rssc.12015
[22] Spencer, S. E. F.; Besser, T. E.; Cobbold, R. N.; French, N. P., ‘Super’ or Just ‘Above Average’? Supershedders and the Transmission of Escherichia coli O157:H7 Among Feedlot Cattle,”, Journal of the Royal Society Interface, 12, 20150446 (2015) · doi:10.1098/rsif.2015.0446
[23] Touloupou, P., Bayesian Inference and Model Selection for Partially Observed Stochastic Epidemics (2016)
[24] Wickham, H., ggplot2: Elegant Graphics for Data Analysis (2016), New York: Springer, New York · Zbl 1397.62006
[25] Zhong, S.; Ghosh, J., HMMs and Coupled HMMs for Multi-Channel EEG Classification, 1154-1159 (2002)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.