×

Bayesian analysis of mixture autoregressive models covering the complete parameter space. (English) Zbl 1505.62333

Summary: Mixture autoregressive (MAR) models provide a flexible way to model time series with predictive distributions which depend on the recent history of the process and are able to accommodate asymmetry and multimodality. Bayesian inference for such models offers the additional advantage of incorporating the uncertainty in the estimated models into the predictions. We introduce a new way of sampling from the posterior distribution of the parameters of MAR models which allows for covering the complete parameter space of the models, unlike previous approaches. We also propose a relabelling algorithm to deal a posteriori with label switching. We apply our new method to simulated and real datasets, discuss the accuracy and performance of our new method, as well as its advantages over previous studies. The idea of density forecasting using MCMC output is also introduced.

MSC:

62-08 Computational methods for problems pertaining to statistics
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62F15 Bayesian inference

Software:

fma; mixAR
PDFBibTeX XMLCite
Full Text: DOI arXiv

References:

[1] Boshnakov, GN, Analytic expressions for predictive distributions in mixture autoregressive models, Stat Probab Lett, 79, 15, 1704-1709 (2009) · Zbl 1166.62301
[2] Boshnakov, GN, On first and second order stationarity of random coefficient models, Linear Algebra Appl, 434, 2, 415-423 (2011) · Zbl 1206.62145
[3] Boshnakov GN, Ravagli D (2020) mixAR: mixture autoregressive models. R package version 0.22.4. https://CRAN.R-project.org/package=mixAR
[4] Box GEP, Jenkins GM (1976) Time series analysis: forecasting and control/George E.P. Box and Gwilym M. Jenkins, rev. ed. edn, Holden-Day San Francisco · Zbl 0363.62069
[5] Celeux G (2000) Bayesian inference of mixture: the label switching problem. In: Payne R, Green P (eds) COMPSTAT. Physica, Heidelberg · Zbl 0951.62018
[6] Chib, S., Marginal likelihood from the Gibbs output, J Am Stat Assoc, 90, 432, 1313-1321 (1995) · Zbl 0868.62027
[7] Chib, S.; Jeliazkov, I., Marginal likelihood from the Metropolis-Hastings output, J Am Stat Assoc, 96, 453, 270-281 (2001) · Zbl 1015.62020
[8] Dempster, AP; Laird, NM; Rubin, DB, Maximum likelihood from incomplete data via the em algorithm, J R Stat Soc Ser B (Methodol), 39, 1-38 (1977) · Zbl 0364.62022
[9] Diebolt, J.; Robert, CP, Estimation of finite mixture distributions through Bayesian sampling, J R Stat Soc Ser B (Methodol), 56, 363-375 (1994) · Zbl 0796.62028
[10] Elton, C.; Nicholson, M., The ten-year cycle in numbers of the lynx in Canada, J Anim Ecol, 11, 2, 215-244 (1942)
[11] Ferguson, TS, A Bayesian analysis of some nonparametric problems, Ann Stat, 1, 2, 209-230 (1973) · Zbl 0255.62037
[12] Green, PJ, Reversible jump Markov chain Monte Carlo computation and Bayesian model determination, Biometrika, 82, 4, 711-732 (1995) · Zbl 0861.62023
[13] Hossain AS (2012) Complete Bayesian analysis of some mixture time series models. PhD thesis, Probability and Statistics Group, School of Mathematics, University of Manchester
[14] Hyndman RJ (2017) fma: data sets from “Forecasting: Methods and Applications” by Makridakis, Wheelwright & Hyndman (1998). R package version 2.3. https://CRAN.R-project.org/package=fma
[15] Jones, MC, Randomly choosing parameters from the stationarity and invertibility region of autoregressive-moving average models, J R Stat Soc Ser C (Appl Stat), 36, 2, 134-138 (1987) · Zbl 0617.62100
[16] Lau, JW; So, MK, Bayesian mixture of autoregressive models, Comput Stat Data Anal, 53, 1, 38-60 (2008) · Zbl 1452.62655
[17] Lawless, JF; Fredette, M., Frequentist prediction intervals and predictive distributions, Biometrika, 92, 3, 529-542 (2005) · Zbl 1183.62052
[18] Le, ND; Martin, R.; Raftery, AE, Modeling flat stretches, bursts, and outliers in time series using mixture transition distribution models, J Am Stat Assoc, 91, 436, 1504-1515 (1996) · Zbl 0881.62096
[19] Lo, AY, Weighted Chinese restaurant processes, COSMOS, 01, 1, 107-111 (2005)
[20] Met Office Centre for Environmental Data Analysis: 2019, Met office midas open: UK land surface stations data (1853-current). data retrieved from the CEDA Archive, http://catalogue.ceda.ac.uk/uuid/dbd451271eb04662beade68da43546e1
[21] Nelson, DB, Conditional heteroskedasticity in asset returns: a new approach, Econom J Econom Soc, 59, 347-370 (1991) · Zbl 0722.62069
[22] Richardson, S.; Green, PJ, On Bayesian analysis of mixtures with an unknown number of components, J R Stat Soc Ser B Stat Methodol, 59, 4, 731-792 (1997) · Zbl 0891.62020
[23] Rousseau, J.; Mengersen, K., Asymptotic behaviour of the posterior distribution in overfitted mixture models, J R Stat Soc Ser B (Stat Methodol), 73, 5, 689-710 (2011) · Zbl 1228.62034
[24] Sampietro, S., Bayesian analysis of mixture of autoregressive components with an application to financial market volatility, Appl Stoch Models Bus Ind, 22, 3, 242 (2006) · Zbl 1115.62088
[25] Tong, H., Non-linear time series: a dynamical system approach (1990), Oxford: Oxford University Press, Oxford · Zbl 0716.62085
[26] Wong, CS; Li, WK, On a mixture autoregressive model, J R Stat Soc Ser B Stat Methodol, 62, 1, 95-115 (2000) · Zbl 0941.62095
[27] Wood, S.; Rosen, O.; Kohn, R., Bayesian mixtures of autoregressive models, J Comput Graph Stat, 20, 1, 174-195 (2011)
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.