Robust identification of highly persistent interest rate regimes. (English) Zbl 1411.62303

Peluso, Stefano; Mira, Antonietta; Muliere, Pietro

Int. J. Approx. Reasoning 83, 102-117 (2017).

Summary: Parametric specifications in State Space Models (SSMs) are a source of bias in case of mismatch between modeling assumptions and reality. We propose a Bayesian semiparametric SSM that is robust to misspecified emission distributions. The Markovian nature of the latent stochastic process creates a temporal dependence and links the random probability distributions of the observations in a mixture of products of Dirichlet processes (MPDP). The model is shown to be adequate and it is applied to simulated data and to the motivating empirical problem of regime shifts in interest rates with latent state persistence.

MSC:

62P05	Applications of statistics to actuarial sciences and financial mathematics
62M05	Markov processes: estimation; hidden Markov models
62G35	Nonparametric robustness

Keywords:

Bayesian nonparametric statistics; hidden Markov models; interest rates; regime shifts; state space model; robust; regime shifts; interest rates

References:

[1]	Albert, J.; Chib, S., Bayes inference via Gibbs sampling of autoregressive time series subject to Markov mean and variance shifts, J. Bus. Econ. Stat., 11, 1-15 (1993)
[2]	Antoniak, C., Mixtures of Dirichlet processes with applications to bayesian nonparametric problems, Ann. Stat., 2, 1152-1174 (1974) · Zbl 0335.60034
[3]	Beal, M.; Ghahramani, Z.; Rasmussen, C., Infinite hidden Markov model, (The 2001 Neural Information Processing Systems (NIPS) Conference. The 2001 Neural Information Processing Systems (NIPS) Conference, British Columbia, Canada. The 2001 Neural Information Processing Systems (NIPS) Conference. The 2001 Neural Information Processing Systems (NIPS) Conference, British Columbia, Canada, Advances in Neural Information Processing Systems, vol. 14 (2002))
[4]	Blackwell, D.; MacQueen, J., Ferguson distribution via Pólya Urn scheme, Ann. Stat., 1, 353-355 (1973) · Zbl 0276.62010
[5]	Cai, J., A Markov model of unconditional variance in ARCH, J. Bus. Econ. Stat., 12, 309-316 (1994)
[6]	Caron, F.; Davy, M.; Doucet, A.; Duflos, E.; Vanheeghe, P., Bayesian inference for linear dynamic models with Dirichlet process mixtures, IEEE Trans. Signal Process., 56, 71-84 (2008) · Zbl 1391.62144
[7]	Carota, C., Two-way layout: a nonparametric Bayesian approach (in Italian), (Proceedings of the 34th Scientific Meetings of the Italian Statistical Society (1988))
[8]	Carota, C.; Parmigiani, G., Semiparametric regression for count data, Biometrika, 89, 265-281 (2002) · Zbl 1017.62035
[9]	Chib, S., Calculating posterior distributions and modal estimates in Markov mixture models, J. Econom., 75, 79-97 (1996) · Zbl 0864.62010
[10]	Chung, Y.; Dunson, D., The local Dirichlet process, Ann. Inst. Stat. Math., 63, 59-80 (2011) · Zbl 1432.62083
[11]	Cifarelli, D., Bayesian nonparametric approach of an analysis of variance problem, Ann. dell’Ist. Mat. Finanz. dell’Univ. Torino, Ser. III, 17, 1-20 (1979), (in Italian)
[12]	Cifarelli, D.; Muliere, P.; Scarsini, M., Il modello lineare nell’approccio bayesiano non parametrico, (Quaderni di Dipartimento, n15 (1981), Istituto di Matematica G. Castelnuovo: Istituto di Matematica G. Castelnuovo Roma). (The Proceedings of the Conference in Honour of Cifarelli (2008)), Translated in English as The linear model within the bayesian nonparametric approach
[13]	Cifarelli, D.; Regazzini, E., Problemi statistici nonparametrici in condizioni di scambiabilit parziale e impiego di medie associative, Quad. Ist. Mat. Finanz. Torino, 12, 1-36 (1978)
[14]	Dalal, S.; Hall, G., On approximating parametric bayes models by nonparametric Bayes models, Ann. Stat., 8, 664-672 (1980) · Zbl 0438.62042
[15]	de Finetti, B., La prévision: ses lois logiques, ses sources subjectives, Ann. Inst. Henri Poincaré, 7, 1-68 (1937) · JFM 63.1070.02
[16]	de Finetti, B., Sur la condition d’equivalence partielle, (VI Colloque Geneve. VI Colloque Geneve, Acta Sci. Ind., vol. 739 (1938), Herman: Herman Paris) · JFM 64.0517.08
[17]	Dempster, A.; Laird, N.; Rubin, D., Maximum likelihood estimation from incomplete data, J. R. Stat. Soc. B, 39, 1-38 (1977) · Zbl 0364.62022
[18]	Diaconis, P.; Freedman, D., De Finetti’s theorem for Markov chains, Ann. Probab., 8, 115-130 (1980) · Zbl 0426.60064
[19]	Doucet, A.; de Freitas, N.; Gordon, N., Sequential Monte Carlo Methods in Practice (2001), Springer: Springer New York · Zbl 0967.00022
[20]	Dueker, M., Conditional heteroscedasticity in qualitative response models of time series: a Gibbs-sampling approach to the bank prime rate, J. Bus. Econ. Stat., 17, 466-472 (1999)
[21]	Dunson, D.; Park, J., Kernel stick-breaking processes, Biometrika, 95, 307-323 (2008) · Zbl 1437.62448
[22]	Escobar, M.; West, M., Bayesian density estimation and inference using mixtures, J. Am. Stat. Assoc., 90, 577-588 (1995) · Zbl 0826.62021
[23]	Ferguson, T., A Bayesian analysis of some nonparametric problems, Ann. Stat., 1, 209-230 (1973) · Zbl 0255.62037
[24]	Ferguson, T., Prior distributions on spaces of probability measures, Ann. Stat., 2, 615-629 (1974) · Zbl 0286.62008
[25]	Florens, J.; Mouchart, M.; Rolin, J., Semi- and non-parametric Bayesian analysis of duration models, Int. Stat. Rev., 67, 187-210 (1999) · Zbl 0968.62033
[26]	Fortini, S.; Ladelli, L.; Petris, G.; Regazzini, E., On mixtures of distributions of Markov chains, Stoch. Process. Appl., 100, 147-165 (2002) · Zbl 1060.60071
[27]	Fox, E.; Sudderth, E.; Jordan, M.; Willsky, A., An HDP-HMM for systems with state persistence, (Proc. of the Int. Conf. on Machine Learning (2008))
[28]	Fox, E.; Sudderth, E.; Jordan, M.; Willsky, A., A sticky HDP-HMM with applications to speaker diarization, Ann. Appl. Stat., 5, 1020-1056 (2011) · Zbl 1232.62077
[29]	Ghosh, A.; Mukhopadhyay, S.; Roy, S.; Bhattacharya, S., Bayesian inference in nonparametric dynamic state-space models, Stat. Methodol., 21, 35-48 (2014) · Zbl 1486.62240
[30]	Gray, S., Modeling the conditional distribution of interest rates as a regime-switching process, J. Financ. Econ., 42, 27-62 (1996)
[31]	Griffin, J.; Steel, M., Order-based dependent Dirichlet processes, J. Am. Stat. Assoc., 101, 179-194 (2006) · Zbl 1118.62360
[32]	Hamilton, J., Rational expectations econometric analysis of changes in regime, J. Econ. Dyn. Control, 12, 385-423 (1988) · Zbl 0661.62117
[33]	Harvey, A., Forecasting, Structural Time Series Models and the Kalman Filter (1991), Cambridge University Press: Cambridge University Press Cambridge
[34]	Kim, C.; Morley, J.; Nelson, C., The structural break in the equity premium, J. Bus. Econ. Stat., 23, 181-191 (2005)
[35]	Korwar, R.; Hollander, M., Contributions to the theory of Dirichlet processes, Ann. Probab., 1, 705-711 (1973) · Zbl 0264.60084
[36]	Li, H.; Fu, M., A linear matrix inequality approach to robust \(H_\infty\) filtering, IEEE Trans. Signal Process., 45, 2338-2350 (1997)
[37]	Lo, A., On a class of Bayesian nonparametric estimates, Ann. Stat., 12, 351-357 (1984) · Zbl 0557.62036
[38]	Montanez, G.; Amizadeh, S.; Laptev, N., Inertial hidden Markov models: modeling change in multivariate time series, (Proceedings of AAAI 2015 (2015))
[39]	Muliere, P.; Giudici, P.; Mezzetti, M., Mixtures of products of Dirichlet processes for variable selection in survival analysis, J. Stat. Plan. Inference, 111, 101-115 (2003) · Zbl 1033.62099
[40]	Muliere, P.; Petrone, S., A Bayesian predictive approach to sequential search for an optimal dose: parametric and nonparametric models, J. Ital. Stat. Soc., 2, 349-364 (1993) · Zbl 1446.62283
[41]	Muliere, P.; Tardella, L., Approximating distributions of random functional of Ferguson-Dirichlet priors, Can. J. Stat., 26, 283-297 (1998) · Zbl 0913.62010
[42]	Petrone, S.; Mira, A., Bayesian hierarchical nonparametric inference for change point problems, Bayesian Stat., 5, 693-703 (1996)
[43]	Petrone, S.; Raftery, A., A note on the Dirichlet process prior in Bayesian nonparametric inference with partial exchangeability, Stat. Probab. Lett., 36, 69-83 (1997) · Zbl 0953.62105
[44]	Sethuraman, J., A constructive definition of Dirichlet priors, Stat. Sin., 4, 639-650 (1994) · Zbl 0823.62007
[45]	Startz, R., Binomial autoregressive moving average models with an application to U.S. recessions, J. Bus. Econ. Stat., 27, 528-543 (2008)
[46]	Teh, Y.; Jordan, M.; Beal, M.; Blei, D., Hierarchical Dirichlet processes, J. Am. Stat. Assoc., 101, 1566-1581 (2006) · Zbl 1171.62349
[47]	Viterbi, A., Error bounds for convolutional codes and an asymptotically optimum decoding algorithm, IEEE Trans. Inf. Theory, 13, 260-269 (1967) · Zbl 0148.40501
[48]	Xie, L.; de Souza, C.; Fu, M., \(H_\infty\) estimation for discrete-time linear uncertain systems, Int. J. Robust Nonlinear Control, 1, 111-123 (1991) · Zbl 0754.93050
[49]	Xie, L.; de Souza, C.; Wang, Y., Robust filtering for a class of discrete-time uncertain nonlinear systems: an \(H_\infty\) approach, Int. J. Robust Nonlinear Control, 6, 297-312 (1996) · Zbl 0851.93030