Autoregressive moving average infinite hidden Markov-switching models

Bauwens, Luc [UCL] Carpentier, Jean-François [Université du Luxembourg] Dufays, Arnaud [Université Laval]

Markov-switching models are usually specified under the assumption that all the parameters change when a regime switch occurs. Relaxing this hypothesis and being able to detect with parameters evolve over time is relevant for interpreting the changes in the dynamics of the series, for specifying models parsimoniously, and may be helpful in forecasting. We propose the class of sticky infinite hidden Markov-switching autoregressive moving average models, in which we disentangle the break dynamics of the mean and the variance parameters. In this class, the number of regimes is possibly infinite and is determined when estimating the model, thus avoiding the need to set this number by a model choice criterion. We develop a new Markov chain Monte Carlo estimation method that solves the path dependence issue due to the moving average component. Empirical results on macroeconomic series illustrate that the proposed class of models dominates the model with fixed parameters in terms of point and density forecasts.

• metadata
• References
• relations

Document type	Article de périodique (Journal article) – Article de recherche
Access type	Accès interdit
Publication date	2017
Language	Anglais
Journal information	"Journal of Business and Economic Statistics" - Vol. 35, no.2, p. 162-182 (2017)
Peer reviewed	yes
Publisher	American Statistical Association
issn	0735-0015
e-issn	1537-2707
Publication status	Publié
Affiliation	UCL - SSH/LIDAM/CORE - Center for operations research and econometrics
Keywords	ARMA ; Bayesian inference ; Dirichlet process ; forecasting
Links	http://hdl.handle.net/2078.1/183791[Handle] https://doi.org/10.1080/07350015.2015.1123636[DOI] https://doi.org/10.6084/m9.figshare.1626689[Dataset]

1. Amisano Gianni, Giacomini Raffaella, Comparing Density Forecasts via Weighted Likelihood Ratio Tests, 10.1198/073500106000000332
2. Atchadé Yves F., Rosenthal Jeffrey S., On adaptive Markov chain Monte Carlo algorithms, 10.3150/bj/1130077595
3. Basawa I. V., Lund Robert, Large Sample Properties of Parameter Estimates for Periodic ARMA Models, 10.1111/1467-9892.00246
4. Bauwens Luc, Dufays Arnaud, Rombouts Jeroen V.K., Marginal likelihood for Markov-switching and change-point GARCH models, 10.1016/j.jeconom.2013.08.017
5. Bauwens Luc, Koop Gary, Korobilis Dimitris, Rombouts Jeroen V.K., The Contribution of Structural Break Models to Forecasting Macroeconomic Series : STRUCTURAL BREAK MODELS IN FORECASTING MACROECONOMIC SERIES, 10.1002/jae.2387
6. Beal M.J., Proceedings of the Twenty-Second Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-06), 23 (2006)
7. Blackwell David, MacQueen James B., Ferguson Distributions Via Polya Urn Schemes, 10.1214/aos/1176342372
8. Chib Siddhartha, Marginal Likelihood from the Gibbs Output, 10.1080/01621459.1995.10476635
9. Chib Siddhartha, Calculating posterior distributions and modal estimates in Markov mixture models, 10.1016/0304-4076(95)01770-4
10. Chib Siddhartha, Estimation and comparison of multiple change-point models, 10.1016/s0304-4076(97)00115-2
11. Del Moral Pierre, Doucet Arnaud, Jasra Ajay, Sequential Monte Carlo samplers, 10.1111/j.1467-9868.2006.00553.x
12. Doornik Jurgen A., A Markov-switching model with component structure for US GNP, 10.1016/j.econlet.2012.10.035
13. Sequential Monte Carlo Methods in Practice, ISBN:9781441928870, 10.1007/978-1-4757-3437-9
14. ———, Journal of Financial Econometrics (2015)
15. Ferguson Thomas S., A Bayesian Analysis of Some Nonparametric Problems, 10.1214/aos/1176342360
16. Fox Emily B., Sudderth Erik B., Jordan Michael I., Willsky Alan S., A sticky HDP-HMM with application to speaker diarization, 10.1214/10-aoas395
17. Francq Christian, Gautier Antony, Estimation of time-varying ARMA models with Markovian changes in regime, 10.1016/j.spl.2004.10.009
18. Francq Christian, Zakoı¨an Jean-Michel, Deriving the autocovariances of powers of Markov-switching GARCH models, with applications to statistical inference, 10.1016/j.csda.2007.08.003
19. Fruhwirth-Schnatter Sylvia, Estimating marginal likelihoods for mixture and Markov switching models using bridge sampling techniques, 10.1111/j.1368-423x.2004.00125.x
20. Geweke John, Bayesian Inference in Econometric Models Using Monte Carlo Integration, 10.2307/1913710
21. Davidson Russell, MacKinnon James G., Improving the reliability of bootstrap tests with the fast double bootstrap, 10.1016/j.csda.2006.04.001
22. Girolami Mark, Calderhead Ben, Riemann manifold Langevin and Hamiltonian Monte Carlo methods : Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods, 10.1111/j.1467-9868.2010.00765.x
23. Gneiting Tilmann, Raftery Adrian E, Strictly Proper Scoring Rules, Prediction, and Estimation, 10.1198/016214506000001437
24. Gneiting Tilmann, Ranjan Roopesh, Comparing Density Forecasts Using Threshold- and Quantile-Weighted Scoring Rules, 10.1198/jbes.2010.08110
25. Goldfeld Stephen M., Quandt Richard E., A Markov model for switching regressions, 10.1016/0304-4076(73)90002-x
26. Goutte Stéphane, Conditional Markov regime switching model applied to economic modelling, 10.1016/j.econmod.2013.12.007
27. Gray Stephen F., Modeling the conditional distribution of interest rates as a regime-switching process, 10.1016/0304-405x(96)00875-6
28. Haas M., A New Approach to Markov-Switching GARCH Models, 10.1093/jjfinec/nbh020
29. Hamilton James D., A New Approach to the Economic Analysis of Nonstationary Time Series and the Business Cycle, 10.2307/1912559
30. Henneke Jan S., Rachev Svetlozar T., Fabozzi Frank J., Nikolov Metodi, MCMC-based estimation of Markov Switching ARMA–GARCH models, 10.1080/00036840802552379
31. Ishwaran Hemant, Zarepour Mahmoud, Exact and approximate sum representations for the Dirichlet process, 10.2307/3315951
32. JASRA AJAY, STEPHENS DAVID A., DOUCET ARNAUD, TSAGARIS THEODOROS, Inference for Lévy-Driven Stochastic Volatility Models via Adaptive Sequential Monte Carlo : Lévy-driven stochastic volatility, 10.1111/j.1467-9469.2010.00723.x
33. Jensen Mark J., Maheu John M., Bayesian semiparametric stochastic volatility modeling, 10.1016/j.jeconom.2010.01.014
34. Jensen Mark J., Maheu John M., Bayesian semiparametric multivariate GARCH modeling, 10.1016/j.jeconom.2013.03.009
35. Jensen Mark J., Maheu John M., Estimating a semiparametric asymmetric stochastic volatility model with a Dirichlet process mixture, 10.1016/j.jeconom.2013.08.018
36. Jochmann Markus, Modeling U.S. Inflation Dynamics: A Bayesian Nonparametric Approach, 10.1080/07474938.2013.806199
37. Kivinen J., Proceedings of the IEEE International Conference on Computer Vision (2007)
38. Klaassen Franc, Improving GARCH volatility forecasts with regime-switching GARCH, 10.1007/s001810100100
39. Kurihara K., Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI-07) (2007)
40. Marin Jean-Michel, Mengersen Kerrie, Robert Christian P., Bayesian Modelling and Inference on Mixtures of Distributions, Handbook of Statistics (2005) ISBN:9780444515391 p.459-507, 10.1016/s0169-7161(05)25016-2
41. Rabiner L.R., A tutorial on hidden Markov models and selected applications in speech recognition, 10.1109/5.18626
42. Sethuraman J., Statistica Sinica, 4, 639 (1994)
43. Song Yong, MODELLING REGIME SWITCHING AND STRUCTURAL BREAKS WITH AN INFINITE HIDDEN MARKOV MODEL : INFINITE HIDDEN MARKOV MODEL, 10.1002/jae.2337
44. STOCK JAMES H., WATSON MARK W., Why Has U.S. Inflation Become Harder to Forecast?, 10.1111/j.1538-4616.2007.00014.x
45. Teh Yee Whye, Jordan Michael I, Beal Matthew J, Blei David M, Hierarchical Dirichlet Processes, 10.1198/016214506000000302
46. Vakilzadeh M., Proceedings of the 9th International Conference on Structural Dynamics, 3029 (2014)
47. Van Gael J., Proceedings of the 25th International Conference on Machine Learning (2008)
48. Xie Wangang, Lewis Paul O., Fan Yu, Kuo Lynn, Chen Ming-Hui, Improving Marginal Likelihood Estimation for Bayesian Phylogenetic Model Selection, 10.1093/sysbio/syq085
49. Xifara T., Sherlock C., Livingstone S., Byrne S., Girolami M., Langevin diffusions and the Metropolis-adjusted Langevin algorithm, 10.1016/j.spl.2014.04.002

See also
	[boreal:157068]	Autoregressive Moving Average Infinite Hidden Markov-Switching Models