Abstract
Time series of proportions arise in many contexts. In this paper, we consider a hidden Markov model (HMM) to describe temporal dependence in such series. In so doing, we introduce a Beta-HMM and develop its Bayesian analysis using Markov Chain Monte Carlo Methods (MCMC). Our proposed model is based on a conjugate prior for beta likelihood which enables us develop Bayesian posterior and predictive computations in an efficient manner. We also address the problem of assessing dimension of the HMM using the marginal likelihood of the model which can be evaluated using posterior samples. Finally, we implement our model and the Bayesian methodology using weekly data on market shares.
Similar content being viewed by others
References
Bayes CL, Bazan JL, Garcia CB (2012) A new robust regression model for proportions. Bayesian Anal 7:841–866
Bayarri MJ (1985) Bayesian inference on the parameters of a beta distribution. Statistics & Decisions (Supplement Issue No. 2):17–21
Billio M, Casarin R (2011) Beta autoregressive transition Markov-switching models for businesscycle analysis. Stud Nonlinear Dyn Econom 15(4)
Bouguila N, Ziou D, Monga E (2006) Practical Bayesian estimation of a finite beta mixture through Gibbs sampling and its applications. Stat Comput 16:215–225
Branscum AJ, Johnson WO, Thurmond MC (2007) Bayesian beta regression: applications to household expenditure data and generic distance between foot-and-mouth disease viruses. Aust N Z J Stat 49:287–301
Casarin R, Valle LD, Leisen F (2012) Bayesian model selection for beta autoregressive processes. Bayesian Anal 7(2)
Cepeda-Cuervo E, Achcar JA, Lopera LG (2014) Bivariate beta regression models: joint modelling of the mean, dispersion and association parameters. J Appl Stat 41(3):677–687
Cepeda-Cuervo E, Garrido L (2015) Bayesian beta regression models with joint mean and dispersion modeling. Monte Carlo Methods Appl 21(1):49–58
Chib S (1995) Marginal likelihood from the Gibbs output. J Am Stat Assoc 90(432):1313–1321
Chib S, Greenberg E (1995) Understanding the Metropolis-Hastings algorithm. Am Stat 49:327–335
Cook DO, Kieschnick R, McCullough BD (2008) Regression analysis of proportions in finance with self selection. J Empir Financ 15(5):860–867
Cox C (1996) Nonlinear quasi-likelihood models: applications to continuous proportions. Computational Statistics & Data Aanalysis 21(4):449–461
Cox DR (1981) Statistical analysis of time series: some recent developments. Scand J Stat 8:93–115
Da-Silva CQ, Migon HS, Correia LT (2011) Dynamic Bayesian beta models. Computational Statistics and Data Analysis 55:2074–2089
Da-Silva CQ, Migon HS (2016) Hierarchical dynamic beta model. REVSTAT Statistical Journal 14(1):49–73
Di Brisco AM, Migliorati S (2020) A new mixed-effects mixture model for constrained longitudinal data. Stat Med 39(2):129–145
Dong AXD, Chan JSK (2013) Bayesian analysis of loss reserving using dynamic models with generalized beta distribution. Insurance: Mathematics and Economics 53(2):355–365
Ferrari S, Cribari-Neto F (2004) Beta regression for modeling rates and proportions. J Appl Stat 31:799–815
Figueroa-Zuniga JI, Arellano-Valle RB, Ferrari SLP (2013) Mixed beta regression: a Bayesian perspective. Comput Stat Data Anal 61:137–147
Fruhwirth-Schnatter S (2004) Finite mixture and Markov-switching models. Springer Series in Statistics
Gelfand AE (1996) Model determination using sampling-based methods. In: Gilks WR, Richardson S, Spiegelhalter DJ (eds) Markov Chain Monte Carlo in Practice. Chapman & Hall, pp 146–161
Grunwald GK, Raftery AE, Guttorp P (1993) Time series of continuous proportions. J R Stat Soc Ser B Stat Methodol 55(1):103–116
Hahn ED (2008) Mixture densities for project management activity times: a robust approach to PERT. Eur J Oper Res 188(2):450–459
Hamilton J (1989) A new approach to the economic analysis of nonstationary time series and the business cycles. Econometrica 57(2):354–384
Hock M, Soyer R (2006) A Bayesian approach to signal analysis of pulse trains. In: Colosimo BM, Del Castillo E (eds) Bayesian Process Monitoring, Control and Optimization. Chapman & Hall, 215-243
Jeffreys H (1935) Some tests of significance threated by the theory of probability. Proceedings of the Cambridge Philosophy Society 31:203–222
Jeffreys H (1961) Theory of probability, 3rd edn. Oxford University Press
Kass RE, Raftery AE (1995) Bayes factors. J Am Stat Assoc 90(430):773–795
Li P (2018) Efficient MCMC estimation of inflated beta regression models. Comput Statistics 33(1):127–158
Ma Z, Leijon A (2011) Bayesian estimation of beta mixture models with variational inference. IEEE Trans Pattern Anal Mach Intell 33(11):2160–2173
Migliorati S, Di Brisco AM, Ongaro A (2018) A new regression model for bounded responses. Bayesian Anal 13(3):845–872
Osthus D, Hickmann KS, Caragea PC, Higdon D, Del Valle SY (2017) Forecasting seasonal influenza with a state-space SIR model. Ann Appl Stat 11(1):202–224
Papke L, Wooldridge JM (1996) Econometric methods for fractional response variables with an application to 401(K) plan participation rates. J Appl Economet 11(6):619–632
Pievatolo A, Ruggeri F, Soyer R (2012) A Bayesian hidden Markov model for imperfect debugging. Reability Engineering and System Safety 103:11–21
Smith JQ (1981) The multiparameter steady model. J R Stat Soc Ser B Methodol 43(2):256–260
Souza D, Moura F (2016) Multivariate beta regression with application in small area estimation. J Off Stat 32(3):747–768
Taddy MA (2010) Autoregressive mixture models for dynamic spatial poisson processes: application to tracking intensity of violent crime. J Am Stat Assoc 105(492):1403–1417
Taufer E (2007) Modelling stylized features in default rates. Appl Stoch Model Bus Ind 23(1):73–82
Wichern DW, Jones RH (1977) Assessing the impact of market disturbances using intervention analysis. Manag Sci 24(3)
Acknowledgements
We would like to thank the Scientific and Technological Research Council of Turkey (TÜBİTAK) for its financial support while the first author was visiting the Department of Decision Sciences at the George Washington University as a research fellow. This paper was completed as a result of this research under TÜBİTAK-2214/A International Doctoral Research Fellowship Programme.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
The posterior probabilities of the hidden states and the MAP Estimation of \({\pmb {X}^{(T)}}\) are given by the following table. Note that the posterior probabilities, which are too small (or large), have been rounded off (see Table 5).
Rights and permissions
About this article
Cite this article
Can, C.E., Ergun, G. & Soyer, R. Bayesian Analysis of Proportions via a Hidden Markov Model. Methodol Comput Appl Probab 24, 3121–3139 (2022). https://doi.org/10.1007/s11009-022-09971-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-022-09971-0