# zbMATH — the first resource for mathematics

Bayesian semi-parametric estimation of the long-memory parameter under FEXP-priors. (English) Zbl 1349.62100
Summary: In this paper we study the semi-parametric problem of the estimation of the long-memory parameter $$d$$ in a Gaussian long-memory model. Considering a family of priors based on FEXP models, called FEXP priors in [the second author et al., Ann. Stat. 40, No. 2, 964–995 (2012; Zbl 1274.62340)], we derive concentration rates together with a Bernstein-von Mises theorem for the posterior distribution of $$d$$, under Sobolev regularity conditions on the short-memory part of the spectral density. Three different variations on the FEXP priors are studied. We prove that one of them leads to the minimax (up to a log $$n$$ term) posterior concentration rate for $$d$$, under Sobolev conditions on the short memory part of the spectral density, while the other two lead to sub-optimal posterior concentration rates in $$d$$. Interestingly these results are contrary to those obtained in [loc. cit.] for the global estimation of the spectral density.

##### MSC:
 62G05 Nonparametric estimation 62F15 Bayesian inference 62G20 Asymptotic properties of nonparametric inference 62M15 Inference from stochastic processes and spectral analysis
longmemo
Full Text:
##### References:
 [1] Arbel, J., Gayraud, G., and Rousseau, J. (2013). Bayesian optimal adaptive estimation using a sieve prior. Scandinavian Journal of Statistics , 40(3):549-570. · Zbl 1364.62102 [2] Beran, J. (1993). Fitting long-memory models by generalized linear regression. Biometrika , 80(4):817-822. · Zbl 0800.62521 [3] Beran, J. (1994). Statistics for long-memory processes , volume 61 of Monographs on Statistics and Applied Probability . Chapman and Hall, New York. · Zbl 0869.60045 [4] Bickel, P. J. and Kleijn, B. J. K. (2012). The semiparametric Bernstein-von Mises theorem. Annals of Statistics , 40:206-237. · Zbl 1246.62081 [5] Castillo, I. (2012). A semiparametric Bernstein-von Mises theorem for Gaussian process priors. Probability Theory and Related Fields , 152(1-2):53-99. · Zbl 1232.62054 [6] Chopin, N., Rousseau, J., and Liseo, B. (2013). Computational aspects of Bayesian spectral density estimation. Journal of Computational and Graphical Statistics , 22(3):533-557. [7] Dahlhaus, R. (1989). Efficient parameter estimation for self-similar processes. Ann. Statist. , 17(4):1749-1766. · Zbl 0703.62091 [8] Freedman, D. (1999). On the Bernstein-von Mises theorem with infinite-dimensional parameters. Ann. Statist. , 27(4):1119-1140. · Zbl 0957.62002 [9] Ghosal, S., Ghosh, J., and van der Vaart, A. (2000). Convergence rates of posterior distributions. The Annals of Statistics , 28(2):500-531. · Zbl 1105.62315 [10] Ghosal, S. and van der Vaart, A. (2007). Convergence rates of posterior distributions for noniid observations. The Annals of Statistics , 35(1):192-225. · Zbl 1114.62060 [11] Hoffmann, M., Rousseau, J., and Schmidt-Hieber, J. (2013). On adaptive posterior concentration rates. ArXiv e-prints . · Zbl 1327.62306 [12] Holan, S., McElroy, T., and Chakraborty, S. (2009). A Bayesian approach to estimating the long memory parameter. Bayesian Anal. , 4(1):159-190. · Zbl 1330.62136 [13] Hurvich, C. M., Moulines, E., and Soulier, P. (2002). The FEXP estimator for potentially non-stationary linear time series. Stochastic Process. Appl. , 97(2):307-340. · Zbl 1057.62074 [14] Iouditsky, A., Moulines, E., and Soulier, P. (2001). Adaptive estimation of the fractional differencing coefficient. Bernoulli , 7(5):699-731. · Zbl 1006.62082 [15] Jensen, M. J. (2004). Semiparametric Bayesian inference of long-memory stochastic volatility models. J. Time Ser. Anal. , 25(6):895-922. · Zbl 1062.62232 [16] Ko, K., Qu, L., and Vannucci, M. (2009). Wavelet-based Bayesian estimation of partially linear regression models with long memory errors. Statist. Sinica , 19(4):1463-1478. · Zbl 1191.62045 [17] Kruijer, W. and Rousseau, J. (2013). Supplement to “Bayesian semi-parametric estimation of the long-memory parameter under FEXP-priors.” DOI:10.1214/13-EJS864SUPP. · Zbl 1349.62100 [18] Li, X. and Zhao, L. H. (2002). Bayesian nonparametric point estimation under a conjugate prior. Stat. Probab. Lett. , 1(4):23-30. · Zbl 1039.62034 [19] Lieberman, O., Rousseau, J., and Zucker, D. M. (2003). Valid asymptotic expansions for the maximum likelihood estimator of the parameter of a stationary, Gaussian, strongly dependent process. Ann. Statist. , 31(2):586-612. Dedicated to the memory of Herbert E. Robbins. · Zbl 1067.62021 [20] Moulines, E. and Soulier, P. (2003). Semiparametric spectral estimation for fractional processes. In Theory and applications of long-range dependence , pages 251-301. Birkhäuser Boston, Boston, MA. · Zbl 1109.62353 [21] Philippe, A. and Rousseau, J. (2002). Non-informative priors in the case of Gaussian long-memory processes. Bernoulli , 8(4):451-473. · Zbl 1003.62026 [22] Rivoirard, V. and Rousseau, J. (2012). Bernstein-von Mises theorem for linear functionals of the density. Ann. Stat. , 40(3):1489-1523. · Zbl 1257.62036 [23] Robinson, P. M. (1994). Time series with strong dependence. In Advances in econometrics, Sixth World Congress, Vol. I (Barcelona, 1990), volume 23 of Econom. Soc. Monogr. , pages 47-95. Cambridge Univ. Press, Cambridge. [24] Robinson, P. M. (1995). Gaussian semiparametric estimation of long range dependence. Ann. Statist. , 23(5):1630-1661. · Zbl 0843.62092 [25] Rousseau, J., Chopin, N., and Liseo, B. (2012). Bayesian nonparametric estimation of the spectral density of a long memory Gaussian process. Annals of Statistics , 40:964-995. · Zbl 1274.62340 [26] Rousseau, J. and Kruijer, W. (2011). Adaptive Bayesian Estimation of a spectral density. · Zbl 1349.62100 [27] van der Vaart, A. W. (1998). Asymptotic statistics , volume 3 of Cambridge Series in Statistical and Probabilistic Mathematics . Cambridge University Press, Cambridge. · Zbl 0910.62001
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. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.