×

Multivariate longitudinal data analysis with mixed effects hidden Markov models. (English) Zbl 1419.62428

Summary: Multiple longitudinal responses are often collected as a means to capture relevant features of the true outcome of interest, which is often hidden and not directly measurable. We outline an approach which models these multivariate longitudinal responses as generated from a hidden disease process. We propose a class of models which uses a hidden Markov model with separate but correlated random effects between multiple longitudinal responses. This approach was motivated by a smoking cessation clinical trial, where a bivariate longitudinal response involving both a continuous and a binomial response was collected for each participant to monitor smoking behavior. A Bayesian method using Markov chain Monte Carlo is used. Comparison of separate univariate response models to the bivariate response models was undertaken. Our methods are demonstrated on the smoking cessation clinical trial dataset, and properties of our approach are examined through extensive simulation studies.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62F15 Bayesian inference
62M05 Markov processes: estimation; hidden Markov models
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Altman, Mixed Hidden Markov models: An extension of the Hidden Markov model to the longitudinal data setting, Journal of the American Statistical Association 102 pp 201– (2007) · Zbl 1284.62803 · doi:10.1198/016214506000001086
[2] Baum, A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains, Annals of Mathematical Statistics 41 pp 164– (1970) · Zbl 0188.49603 · doi:10.1214/aoms/1177697196
[3] DeSantis, Hidden Markov models for zero-inflated Poisson counts with an application to substance use, Statistics in Medicine 30 pp 1678– (2011) · doi:10.1002/sim.4207
[4] Garcia-Zattera, Modeling of multivariate monotone disease processes in the presence of misclassification, Journal of the American Statistical Association 107 pp 976– (2012) · Zbl 1395.62339 · doi:10.1080/01621459.2012.682804
[5] Geman, Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images, IEEE Transactions on Pattern Analysis and Machine Intelligence 6 pp 721– (1984) · Zbl 0573.62030 · doi:10.1109/TPAMI.1984.4767596
[6] Green, Reversible jump Markov chain Monte Carlo computation and Bayesian model determination, Biometrika 82 pp 711– (1995) · Zbl 0861.62023 · doi:10.1093/biomet/82.4.711
[7] Haario, An adaptive Metropolis algorithm, Bernoulli 7 pp 223– (2001) · Zbl 0989.65004 · doi:10.2307/3318737
[8] Hughes, Measures of abstinence in clinical trials: Issues and recommendations, Nicotine and Tobacco Research 5 pp 13– (2003) · doi:10.1080/1462220031000070552
[9] Killeen, Markov model for smoking cessation, Proceedings of the National Academy of Science 108 pp 15549– (2011) · doi:10.1073/pnas.1011277108
[10] Luo, A Bayesian approach to joint analysis of multivariate longitudinal data and parametric accelerated failure time, Statistics in Medicine 33 pp 580– (2014) · doi:10.1002/sim.5956
[11] Maruotti, A semiparametric approach to hidden Markov models under longitudinal observations, Statistics and Computing 19 pp 371– (2009) · doi:10.1007/s11222-008-9099-2
[12] Maruotti, Mixed hidden Markov models for longitudinal data: An overview, International Statistical Review 79 pp 427– (2011) · Zbl 1238.62094 · doi:10.1111/j.1751-5823.2011.00160.x
[13] O’Malley, A controlled trial of naltrexone augmentation of Nicotine replacement therapy for smoking cessation, Archives of Internal Medicine 166 pp 667– (2006) · doi:10.1001/archinte.166.6.667
[14] Patrick, The validity of self-reported smoking: A review and meta-analysis, American Journal of Public Health 84 pp 1086– (1994) · doi:10.2105/AJPH.84.7.1086
[15] Proust-Lima, Joint modelling of multivariate longitudinal outcomes and a time-to-event: A nonlinear latent class approach, Computational Statistics & Data Analysis 53 pp 1142– (2009) · Zbl 1452.62841 · doi:10.1016/j.csda.2008.10.017
[16] Rosychuk, Parameter estimation in a model for misclassified Markov data-A Bayesian approach, Computational Statistics and Data Analysis 53 pp 3805– (2009) · Zbl 1453.62187 · doi:10.1016/j.csda.2009.04.002
[17] Scott, Bayesian methods for hidden Markov models: Recursive computing in the 21st century, Journal of the American Statistical Association 97 pp 337– (2002) · Zbl 1073.65503 · doi:10.1198/016214502753479464
[18] Scott, Hidden Markov models for longitudinal comparisons, Journal of the American Statistical Association 100 pp 359– (2005) · Zbl 1117.62421 · doi:10.1198/016214504000001592
[19] Shirley, Hidden Markov models for alcoholism treatment trial data, Annals of Applied Statistics 4 pp 366– (2010) · Zbl 1189.62176 · doi:10.1214/09-AOAS282
[20] Smith, Bayesian computation via the Gibbs sampler and related Markov chain Monte Carlo methods (with discussion), Journal of the Royal Statistical Society, Series B 55 pp 3– (1993) · Zbl 0779.62030
[21] Stephens, Dealing with label switching in mixture models, Journal of the Royal Statistical Society, Series B 62 pp 795– (2000) · Zbl 0957.62020 · doi:10.1111/1467-9868.00265
[22] Verbeke, The analysis of multivariate longitudinal data: A review, Statistical Methods in Medical Research 23 pp 42– (2014) · doi:10.1177/0962280212445834
[23] Watanabe, Asymptotic equivalence of Bayes cross validation and widely applicable information criterion in singular learning theory, Journal of Machine Learning Research 11 pp 3571– (2010) · Zbl 1242.62024
[24] Xiong, A binning method for analyzing mixed longitudinal data measured at distinct time points, Statistics in Medicine 29 pp 1919– (2010) · doi:10.1002/sim.3953
[25] Zucchini, Hidden Markov Models for Time Series: An Introduction Using R (2009) · Zbl 1180.62130 · doi:10.1201/9781420010893
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.