Bernoulli

  • Bernoulli
  • Volume 24, Number 3 (2018), 1860-1909.

Strong consistency of multivariate spectral variance estimators in Markov chain Monte Carlo

Dootika Vats, James M. Flegal, and Galin L. Jones

Full-text: Access denied (no subscription detected)

We're sorry, but we are unable to provide you with the full text of this article because we are not able to identify you as a subscriber. If you have a personal subscription to this journal, then please login. If you are already logged in, then you may need to update your profile to register your subscription. Read more about accessing full-text

Abstract

Markov chain Monte Carlo (MCMC) algorithms are used to estimate features of interest of a distribution. The Monte Carlo error in estimation has an asymptotic normal distribution whose multivariate nature has so far been ignored in the MCMC community. We present a class of multivariate spectral variance estimators for the asymptotic covariance matrix in the Markov chain central limit theorem and provide conditions for strong consistency. We examine the finite sample properties of the multivariate spectral variance estimators and its eigenvalues in the context of a vector autoregressive process of order 1.

Article information

Source
Bernoulli Volume 24, Number 3 (2018), 1860-1909.

Dates
Received: January 2016
Revised: June 2016
First available in Project Euclid: 2 February 2018

Permanent link to this document
https://projecteuclid.org/euclid.bj/1517540462

Digital Object Identifier
doi:10.3150/16-BEJ914

Keywords
Markov chain Monte Carlo spectral methods standard errors

Citation

Vats, Dootika; Flegal, James M.; Jones, Galin L. Strong consistency of multivariate spectral variance estimators in Markov chain Monte Carlo. Bernoulli 24 (2018), no. 3, 1860--1909. doi:10.3150/16-BEJ914. https://projecteuclid.org/euclid.bj/1517540462


Export citation

References

  • [1] Acosta, F., Huber, M.L. and Jones, G.L. (2015). Markov chain Monte Carlo with linchpin variables. Preprint.
  • [2] Anderson, T.W. (1971). The Statistical Analysis of Time Series. New York–London–Sydney: Wiley.
  • [3] Andrews, D.W.K. (1991). Heteroskedasticity and autocorrelation consistent covariance matrix estimation. Econometrica 59 817–858.
  • [4] Atchadé, Y.F. (2011). Kernel estimators of asymptotic variance for adaptive Markov chain Monte Carlo. Ann. Statist. 39 990–1011.
  • [5] Berkes, I. and Philipp, W. (1979). Approximation theorems for independent and weakly dependent random vectors. Ann. Probab. 7 29–54.
  • [6] Billingsley, P. (2008). Probability and Measure. New York: Wiley.
  • [7] Choi, H.M. and Hobert, J.P. (2013). The Polya-Gamma Gibbs sampler for Bayesian logistic regression is uniformly ergodic. Electron. J. Stat. 7 2054–2064.
  • [8] Chow, Y.S. and Teicher, H. (1978). Probability Theory: Independence, Interchangeability, Martingales. New York–Heidelberg: Springer.
  • [9] Csörgő, M. and Révész, P. (1981). Strong Approximations in Probability and Statistics. Probability and Mathematical Statistics. New York–London: Academic Press.
  • [10] Damerdji, H. (1991). Strong consistency and other properties of the spectral variance estimator. Manage. Sci. 37 1424–1440.
  • [11] de Jong, R.M. (2000). A strong consistency proof for heteroskedasticity and autocorrelation consistent covariance matrix estimators. Econometric Theory 16 262–268.
  • [12] Dehling, H. and Philipp, W. (1982). Almost sure invariance principles for weakly dependent vector-valued random variables. Ann. Probab. 10 689–701.
  • [13] Doss, C.R., Flegal, J.M., Jones, G.L. and Neath, R.C. (2014). Markov chain Monte Carlo estimation of quantiles. Electron. J. Stat. 8 2448–2478.
  • [14] Doss, H. and Hobert, J.P. (2010). Estimation of Bayes factors in a class of hierarchical random effects models using a geometrically ergodic MCMC algorithm. J. Comput. Graph. Statist. 19 295–312.
  • [15] Eberlein, E. (1986). On strong invariance principles under dependence assumptions. Ann. Probab. 14 260–270.
  • [16] Einmahl, U. (1989). Extensions of results of Komlós, Major, and Tusnády to the multivariate case. J. Multivariate Anal. 28 20–68.
  • [17] Flegal, J.M. and Gong, L. (2015). Relative fixed-width stopping rules for Markov chain Monte Carlo simulations. Statist. Sinica 25 655–675.
  • [18] Flegal, J.M., Haran, M. and Jones, G.L. (2008). Markov chain Monte Carlo: Can we trust the third significant figure? Statist. Sci. 23 250–260.
  • [19] Flegal, J.M. and Jones, G.L. (2010). Batch means and spectral variance estimators in Markov chain Monte Carlo. Ann. Statist. 38 1034–1070.
  • [20] Flegal, J.M. and Jones, G.L. (2011). Implementing MCMC: Estimating with confidence. In Handbook of Markov Chain Monte Carlo (S. Brooks, A. Gelman, X.L. Meng and G.L. Jones, eds.). Boca Raton, FL: Chapman & Hall.
  • [21] Fort, G. and Moulines, E. (2003). Polynomial ergodicity of Markov transition kernels. Stochastic Process. Appl. 103 57–99.
  • [22] Franklin, J.N. (2012). Matrix Theory. Courier Corporation.
  • [23] Geyer, C.J. (1992). Practical Markov chain Monte Carlo (with discussion). Statist. Sci. 7 473–511.
  • [24] Geyer, C.J. (2011). Introduction to Markov chain Monte Carlo. In Handbook of Markov Chain Monte Carlo (S. Brooks, A. Gelman, G.L. Jones and X.L. Meng, eds.). Boca Raton, FL: Chapman & Hall.
  • [25] Glynn, P.W. and Whitt, W. (1992). The asymptotic validity of sequential stopping rules for stochastic simulations. Ann. Appl. Probab. 2 180–198.
  • [26] Gong, L. and Flegal, J.M. (2016). A practical sequential stopping rule for high-dimensional Markov chain Monte Carlo. J. Comput. Graph. Statist. 25 684–700.
  • [27] Hobert, J.P. and Geyer, C.J. (1998). Geometric ergodicity of Gibbs and block Gibbs samplers for a hierarchical random effects model. J. Multivariate Anal. 67 414–430.
  • [28] Hobert, J.P., Jones, G.L., Presnell, B. and Rosenthal, J.S. (2002). On the applicability of regenerative simulation in Markov chain Monte Carlo. Biometrika 89 731–743.
  • [29] Horváth, L. (1984). Strong approximation of extended renewal processes. Ann. Probab. 12 1149–1166.
  • [30] Jarner, S.F. and Hansen, E. (2000). Geometric ergodicity of Metropolis algorithms. Stochastic Process. Appl. 85 341–361.
  • [31] Jarner, S.F. and Roberts, G.O. (2002). Polynomial convergence rates of Markov chains. Ann. Appl. Probab. 12 224–247.
  • [32] Jarner, S.F. and Roberts, G.O. (2007). Convergence of heavy-tailed Monte Carlo Markov chain algorithms. Scand. J. Stat. 34 781–815.
  • [33] Johnson, A.A. and Jones, G.L. (2015). Geometric ergodicity of random scan Gibbs samplers for hierarchical one-way random effects models. J. Multivariate Anal. 140 325–342.
  • [34] Johnson, L.T. and Geyer, C.J. (2012). Variable transformation to obtain geometric ergodicity in the random-walk Metropolis algorithm. Ann. Statist. 40 3050–3076.
  • [35] Jones, G.L. (2004). On the Markov chain central limit theorem. Probab. Surv. 1 299–320.
  • [36] Jones, G.L., Haran, M., Caffo, B.S. and Neath, R. (2006). Fixed-width output analysis for Markov chain Monte Carlo. J. Amer. Statist. Assoc. 101 1537–1547.
  • [37] Jones, G.L. and Hobert, J.P. (2001). Honest exploration of intractable probability distributions via Markov chain Monte Carlo. Statist. Sci. 16 312–334.
  • [38] Jones, G.L., Roberts, G.O. and Rosenthal, J.S. (2014). Convergence of conditional Metropolis–Hastings samplers. Adv. in Appl. Probab. 46 422–445.
  • [39] Kass, R.E., Carlin, B.P., Gelman, A. and Neal, R.M. (1998). Markov chain Monte Carlo in practice: A roundtable discussion. Amer. Statist. 52 93–100.
  • [40] Komlós, J., Major, P. and Tusnády, G. (1975). An approximation of partial sums of independent ${\mathrm{RV}}$’s and the sample ${\mathrm{DF}}$. I. Z. Wahrsch. Verw. Gebiete 32 111–131.
  • [41] Kosorok, M.R. (2000). Monte Carlo error estimation for multivariate Markov chains. Statist. Probab. Lett. 46 85–93.
  • [42] Kuelbs, J. and Philipp, W. (1980). Almost sure invariance principles for partial sums of mixing $B$-valued random variables. Ann. Probab. 8 1003–1036.
  • [43] Liu, J.S. (2008). Monte Carlo Strategies in Scientific Computing. Springer Series in Statistics. New York: Springer.
  • [44] Marchev, D. and Hobert, J.P. (2004). Geometric ergodicity of van Dyk and Meng’s algorithm for the multivariate Student’s $t$ model. J. Amer. Statist. Assoc. 99 228–238.
  • [45] Meyn, S. and Tweedie, R.L. (2009). Markov Chains and Stochastic Stability, 2nd ed. Cambridge: Cambridge Univ. Press.
  • [46] Mykland, P., Tierney, L. and Yu, B. (1995). Regeneration in Markov chain samplers. J. Amer. Statist. Assoc. 90 233–241.
  • [47] Petrone, S., Roberts, G.O. and Rosenthal, J.S. (1999). A note on convergence rates of Gibbs sampling for nonparametric mixtures. Far East J. Theor. Stat. 3 213–225.
  • [48] Philipp, W. and Stout, W.F. (1975). Almost Sure Invariance Principles for Partial Sums of Weakly Dependent Random Variables 161. Providence, RI: AMS.
  • [49] Polson, N.G., Scott, J.G. and Windle, J. (2013). Bayesian inference for logistic models using Pólya–Gamma latent variables. J. Amer. Statist. Assoc. 108 1339–1349.
  • [50] Robert, C.P. and Casella, G. (2004). Monte Carlo Statistical Methods, 2nd ed. Springer Texts in Statistics. New York: Springer.
  • [51] Roberts, G.O. and Rosenthal, J.S. (1999). Convergence of slice sampler Markov chains. J. R. Stat. Soc. Ser. B. Stat. Methodol. 61 643–660.
  • [52] Roberts, G.O. and Rosenthal, J.S. (2004). General state space Markov chains and MCMC algorithms. Probab. Surv. 1 20–71.
  • [53] Roberts, G.O. and Tweedie, R.L. (1996). Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms. Biometrika 83 95–110.
  • [54] Rosenthal, J.S. (1996). Analysis of the Gibbs sampler for a model related to James–Stein estimators. Stat. Comput. 6 269–275.
  • [55] Roy, V. and Hobert, J.P. (2007). Convergence rates and asymptotic standard errors for Markov chain Monte Carlo algorithms for Bayesian probit regression. J. R. Stat. Soc. Ser. B. Stat. Methodol. 69 607–623.
  • [56] Strassen, V. (1964). An invariance principle for the law of the iterated logarithm. Z. Wahrsch. Verw. Gebiete 3 211–226.
  • [57] Tan, A. and Hobert, J.P. (2009). Block Gibbs sampling for Bayesian random effects models with improper priors: Convergence and regeneration. J. Comput. Graph. Statist. 18 861–878.
  • [58] Tan, A., Jones, G.L. and Hobert, J.P. (2013). On the geometric ergodicity of two-variable Gibbs samplers. In Advances in Modern Statistical Theory and Applications: A Festschrift in Honor of Morris L. Eaton (G.L. Jones and X. Shen, eds.) 25–42. Beachwood, OH: IMS.
  • [59] Tierney, L. (1994). Markov chains for exploring posterior distributions. Ann. Statist. 22 1701–1762.
  • [60] Tjøstheim, D. (1990). Non-linear time series and Markov chains. Adv. in Appl. Probab. 22 587–611.
  • [61] Vats, D., Flegal, J.M. and Jones, G.L. (2016). Multivariate output analysis for Markov chain Monte Carlo. Preprint. Available at arXiv:1512.07713.
  • [62] Whittle, P. (1960). Bounds for the moments of linear and quadratic forms in independent variables. Theory Probab. Appl. 5 302–305.
  • [63] Wu, W.B. (2007). Strong invariance principles for dependent random variables. Ann. Probab. 35 2294–2320.
  • [64] Zaitsev, A.Y. (1998). Multidimensional version of the results of Komlós, Major and Tusnády for vectors with finite exponential moments. ESAIM Probab. Stat. 2 41–108 (electronic).