Statistical Science

Component-Wise Markov Chain Monte Carlo: Uniform and Geometric Ergodicity under Mixing and Composition

Alicia A. Johnson, Galin L. Jones, and Ronald C. Neath

Full-text: Open access

Enhanced PDF (366 KB)

Abstract

It is common practice in Markov chain Monte Carlo to update the simulation one variable (or sub-block of variables) at a time, rather than conduct a single full-dimensional update. When it is possible to draw from each full-conditional distribution associated with the target this is just a Gibbs sampler. Often at least one of the Gibbs updates is replaced with a Metropolis–Hastings step, yielding a Metropolis–Hastings-within-Gibbs algorithm. Strategies for combining component-wise updates include composition, random sequence and random scans. While these strategies can ease MCMC implementation and produce superior empirical performance compared to full-dimensional updates, the theoretical convergence properties of the associated Markov chains have received limited attention. We present conditions under which some component-wise Markov chains converge to the stationary distribution at a geometric rate. We pay particular attention to the connections between the convergence rates of the various component-wise strategies. This is important since it ensures the existence of tools that an MCMC practitioner can use to be as confident in the simulation results as if they were based on independent and identically distributed samples. We illustrate our results in two examples including a hierarchical linear mixed model and one involving maximum likelihood estimation for mixed models.

Article information

Source
Statist. Sci., Volume 28, Number 3 (2013), 360-375.

Dates
First available in Project Euclid: 28 August 2013

Permanent link to this document
https://projecteuclid.org/euclid.ss/1377696941

Digital Object Identifier
doi:10.1214/13-STS423

Mathematical Reviews number (MathSciNet)
MR3135537

Zentralblatt MATH identifier
1331.60151

Keywords
Geometric ergodicity uniform ergodicity Markov chain Monte Carlo Gibbs sampler Metropolis-within-Gibbs random scan convergence rate

Citation

Johnson, Alicia A.; Jones, Galin L.; Neath, Ronald C. Component-Wise Markov Chain Monte Carlo: Uniform and Geometric Ergodicity under Mixing and Composition. Statist. Sci. 28 (2013), no. 3, 360--375. doi:10.1214/13-STS423. https://projecteuclid.org/euclid.ss/1377696941


Export citation

References

  • Atchadé, Y. F. (2011). Kernel estimators of asymptotic variance for adaptive Markov chain Monte Carlo. Ann. Statist. 39 990–1011.
    Mathematical Reviews (MathSciNet): MR2816345
    Digital Object Identifier: doi:10.1214/10-AOS828
    Project Euclid: euclid.aos/1302268084
  • Bédard, M. and Rosenthal, J. S. (2008). Optimal scaling of Metropolis algorithms: Heading toward general target distributions. Canad. J. Statist. 36 483–503.
    Mathematical Reviews (MathSciNet): MR2532248
    Digital Object Identifier: doi:10.1002/cjs.5550360401
  • Booth, J. G. and Hobert, J. P. (1999). Maximizing generalized linear mixed model likelihoods with an automated Monte Carlo EM algorithm. J. R. Stat. Soc. Ser. B Stat. Methodol. 61 265–285.
  • Caffo, B. S., Jank, W. and Jones, G. L. (2005). Ascent-based Monte Carlo expectation-maximization. J. R. Stat. Soc. Ser. B Stat. Methodol. 67 235–251.
    Mathematical Reviews (MathSciNet): MR2137323
    Digital Object Identifier: doi:10.1111/j.1467-9868.2005.00499.x
  • Christensen, O. F., Møller, J. and Waagepetersen, R. P. (2001). Geometric ergodicity of Metropolis–Hastings algorithms for conditional simulation in generalized linear mixed models. Methodol. Comput. Appl. Probab. 3 309–327.
    Mathematical Reviews (MathSciNet): MR1891114
    Digital Object Identifier: doi:10.1023/A:1013779208892
  • Coull, B. A., Hobert, J. P., Ryan, L. M. and Holmes, L. B. (2001). Crossed random effect models for multiple outcomes in a study of teratogenesis. J. Amer. Statist. Assoc. 96 1194–1204.
    Mathematical Reviews (MathSciNet): MR1946573
    Digital Object Identifier: doi:10.1198/016214501753381841
  • Diaconis, P., Khare, K. and Saloff-Coste, L. (2008). Gibbs sampling, exponential families and orthogonal polynomials. Statist. Sci. 23 151–178.
    Mathematical Reviews (MathSciNet): MR2446500
    Digital Object Identifier: doi:10.1214/07-STS252
    Project Euclid: euclid.ss/1219339107
  • 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.
    Mathematical Reviews (MathSciNet): MR2675092
    Digital Object Identifier: doi:10.1198/jcgs.2010.09182
  • 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.
    Mathematical Reviews (MathSciNet): MR2516823
    Digital Object Identifier: doi:10.1214/08-STS257
    Project Euclid: euclid.ss/1219339116
  • Flegal, J. M. and Jones, G. L. (2010). Batch means and spectral variance estimators in Markov chain Monte Carlo. Ann. Statist. 38 1034–1070.
    Mathematical Reviews (MathSciNet): MR2604704
    Digital Object Identifier: doi:10.1214/09-AOS735
    Project Euclid: euclid.aos/1266586622
  • Flegal, J. M. and Jones, G. L. (2011). Implementing Markov chain Monte Carlo: Estimating with confidence. In Handbook of Markov Chain Monte Carlo (S. P. Brooks, A. Gelman, G. L. Jones and X. L. Meng, eds.). CRC Press, Boca Raton, FL.
    Mathematical Reviews (MathSciNet): MR2742422
  • Fort, G., Moulines, E., Roberts, G. O. and Rosenthal, J. S. (2003). On the geometric ergodicity of hybrid samplers. J. Appl. Probab. 40 123–146.
    Mathematical Reviews (MathSciNet): MR1953771
    Digital Object Identifier: doi:10.1239/jap/1044476831
    Project Euclid: euclid.jap/1044476831
  • Geyer, C. (1999). Likelihood inference for spatial point processes. In Stochastic Geometry (Toulouse, 1996) (O. E. Barndorff-Nielsen, W. S. Kendall and M. N. M. van Lieshout, eds.). Monographs on Statistics and Applied Probability 80 79–140. Chapman & Hall/CRC, Boca Raton, FL.
    Mathematical Reviews (MathSciNet): MR1673118
  • Hobert, J. P. (2000). Hierarchical models: A current computational perspective. J. Amer. Statist. Assoc. 95 1312–1316.
    Mathematical Reviews (MathSciNet): MR1825284
    Digital Object Identifier: doi:10.1080/01621459.2000.10474338
  • Hobert, J. P. (2011). The data augmentation algorithm: Theory and methodology. In Handbook of Markov Chain Monte Carlo (S. P. Brooks, A. Gelman, G. L. Jones and X. L. Meng, eds.). CRC Press, Boca Raton, FL.
    Mathematical Reviews (MathSciNet): MR2742422
  • 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.
    Mathematical Reviews (MathSciNet): MR1659196
    Digital Object Identifier: doi:10.1006/jmva.1998.1778
  • 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.
    Mathematical Reviews (MathSciNet): MR1946508
    Digital Object Identifier: doi:10.1093/biomet/89.4.731
  • Jarner, S. F. and Hansen, E. (2000). Geometric ergodicity of Metropolis algorithms. Stochastic Process. Appl. 85 341–361.
    Mathematical Reviews (MathSciNet): MR1731030
    Digital Object Identifier: doi:10.1016/S0304-4149(99)00082-4
  • 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.
    Mathematical Reviews (MathSciNet): MR3097969
    Project Euclid: euclid.aos/1361542074
  • Johnson, A. A. and Jones, G. L. (2010). Gibbs sampling for a Bayesian hierarchical general linear model. Electron. J. Stat. 4 313–333.
    Mathematical Reviews (MathSciNet): MR2645487
    Digital Object Identifier: doi:10.1214/09-EJS515
    Project Euclid: euclid.ejs/1268655652
  • Johnson, A. A., Jones, G. L. and Neath, R. C. (2013). Supplement to “Component-Wise Markov Chain Monte Carlo: Uniform and Geometric Ergodicity Under Mixing and Composition.” DOI:10.1214/13-STS423SUPP.
    Mathematical Reviews (MathSciNet): MR3135537
    Digital Object Identifier: doi:10.1214/13-STS423
    Project Euclid: euclid.ss/1377696941
  • Jones, G. L. and Hobert, J. P. (2001). Honest exploration of intractable probability distributions via Markov chain Monte Carlo. Statist. Sci. 16 312–334.
    Mathematical Reviews (MathSciNet): MR1888447
    Digital Object Identifier: doi:10.1214/ss/1015346317
    Project Euclid: euclid.ss/1015346317
  • Jones, G. L. and Hobert, J. P. (2004). Sufficient burn-in for Gibbs samplers for a hierarchical random effects model. Ann. Statist. 32 784–817.
    Mathematical Reviews (MathSciNet): MR2060178
    Digital Object Identifier: doi:10.1214/009053604000000184
    Project Euclid: euclid.aos/1083178947
  • Jones, G. L., Roberts, G. O. and Rosenthal, J. S. (2013). Convergence of conditional Metropolis–Hastings samplers. J. Appl. Probab. To appear.
    Mathematical Reviews (MathSciNet): MR3215540
    Digital Object Identifier: doi:10.1239/aap/1401369701
    Project Euclid: euclid.aap/1401369701
  • 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.
    Mathematical Reviews (MathSciNet): MR2279478
    Digital Object Identifier: doi:10.1198/016214506000000492
  • Łatuszynski, K., Roberts, G. O. and Rosenthal, J. S. (2013). Adaptive Gibbs samplers and related MCMC methods. Ann. Appl. Probab. 23 66–98.
    Mathematical Reviews (MathSciNet): MR3059204
    Digital Object Identifier: doi:10.1214/11-AAP806
    Project Euclid: euclid.aoap/1359124382
  • Lee, K. J., Jones, G. L., Caffo, B. S. and Bassett, S. (2013). Spatial Bayesian variable selection models on functional magnetic resonance imaging time-series data. Preprint.
  • 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.
    Mathematical Reviews (MathSciNet): MR2054301
    Digital Object Identifier: doi:10.1198/016214504000000223
  • McCulloch, C. E. (1997). Maximum likelihood algorithms for generalized linear mixed models. J. Amer. Statist. Assoc. 92 162–170.
    Mathematical Reviews (MathSciNet): MR1436105
    Digital Object Identifier: doi:10.1080/01621459.1997.10473613
  • Mengersen, K. L. and Tweedie, R. L. (1996). Rates of convergence of the Hastings and Metropolis algorithms. Ann. Statist. 24 101–121.
    Mathematical Reviews (MathSciNet): MR1389882
    Digital Object Identifier: doi:10.1214/aos/1033066201
    Project Euclid: euclid.aos/1033066201
  • Meyn, S. P. and Tweedie, R. L. (1993). Markov Chains and Stochastic Stability. Springer, London.
    Mathematical Reviews (MathSciNet): MR1287609
  • Meyn, S. P. and Tweedie, R. L. (1994). Computable bounds for geometric convergence rates of Markov chains. Ann. Appl. Probab. 4 981–1011.
    Mathematical Reviews (MathSciNet): MR1304770
    Digital Object Identifier: doi:10.1214/aoap/1177004900
    Project Euclid: euclid.aoap/1177004900
  • Neal, P. and Roberts, G. (2006). Optimal scaling for partially updating MCMC algorithms. Ann. Appl. Probab. 16 475–515.
    Mathematical Reviews (MathSciNet): MR2244423
    Digital Object Identifier: doi:10.1214/105051605000000791
    Project Euclid: euclid.aoap/1151592241
  • Neath, R. C. (2013). On convergence properties of the Monte Carlo EM algorithm. In Advances in Modern Statistical Theory and Applications: A Festschrift in Honor of Morris L. Eaton (G. L. Jones and X. Shen, eds.). To appear.
  • Papaspiliopoulos, O. and Roberts, G. (2008). Stability of the Gibbs sampler for Bayesian hierarchical models. Ann. Statist. 36 95–117.
    Mathematical Reviews (MathSciNet): MR2387965
    Digital Object Identifier: doi:10.1214/009053607000000749
    Project Euclid: euclid.aos/1201877295
  • Robert, C. P. (1995). Convergence control methods for Markov chain Monte Carlo algorithms. Statist. Sci. 10 231–253.
    Mathematical Reviews (MathSciNet): MR1390517
    Digital Object Identifier: doi:10.1214/ss/1177009937
    Project Euclid: euclid.ss/1177009937
  • Roberts, G. O. and Polson, N. G. (1994). On the geometric convergence of the Gibbs sampler. J. R. Stat. Soc. Ser. B Stat. Methodol. 56 377–384.
    Mathematical Reviews (MathSciNet): MR1281941
  • Roberts, G. O. and Rosenthal, J. S. (1997). Geometric ergodicity and hybrid Markov chains. Electron. Commun. Probab. 2 13–25 (electronic).
    Mathematical Reviews (MathSciNet): MR1448322
    Digital Object Identifier: doi:10.1214/ECP.v2-981
  • Roberts, G. O. and Rosenthal, J. S. (1998). Two convergence properties of hybrid samplers. Ann. Appl. Probab. 8 397–407.
    Mathematical Reviews (MathSciNet): MR1624941
    Digital Object Identifier: doi:10.1214/aoap/1028903533
    Project Euclid: euclid.aoap/1028903533
  • 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.
    Mathematical Reviews (MathSciNet): MR1707866
    Digital Object Identifier: doi:10.1111/1467-9868.00198
  • Roberts, G. O. and Rosenthal, J. S. (2001). Markov chains and de-initializing processes. Scand. J. Stat. 28 489–504.
    Mathematical Reviews (MathSciNet): MR1858413
    Digital Object Identifier: doi:10.1111/1467-9469.00250
  • Roberts, G. O. and Rosenthal, J. S. (2004). General state space Markov chains and MCMC algorithms. Probab. Surv. 1 20–71.
    Mathematical Reviews (MathSciNet): MR2095565
    Digital Object Identifier: doi:10.1214/154957804100000024
    Project Euclid: euclid.ps/1099928648
  • Roberts, G. O. and Sahu, S. K. (1997). Updating schemes, correlation structure, blocking and parameterization for the Gibbs sampler. J. R. Stat. Soc. Ser. B Stat. Methodol. 59 291–317.
    Mathematical Reviews (MathSciNet): MR1440584
    Digital Object Identifier: doi:10.1111/1467-9868.00070
  • Roberts, G. O. and Tweedie, R. L. (1996). Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms. Biometrika 83 95–110.
    Mathematical Reviews (MathSciNet): MR1399158
    Digital Object Identifier: doi:10.1093/biomet/83.1.95
  • Román, J. C. (2012). Convergence analysis of block Gibbs samplers for Bayesian general linear mixed models. Ph.D. thesis, Dept. Statistics, Univ. Florida.
  • Román, J. C. and Hobert, J. P. (2012). Convergence analysis of the Gibbs sampler for Bayesian general linear mixed models with improper priors. Ann. Statist. 40 2823–2849.
    Mathematical Reviews (MathSciNet): MR3097961
    Digital Object Identifier: doi:10.1214/12-AOS1052
    Project Euclid: euclid.aos/1360332185
  • Rosenthal, J. S. (1995). Minorization conditions and convergence rates for Markov chain Monte Carlo. J. Amer. Statist. Assoc. 90 558–566.
    Mathematical Reviews (MathSciNet): MR1340509
    Digital Object Identifier: doi:10.1080/01621459.1995.10476548
  • Rosenthal, J. S. (1996). Analysis of the Gibbs sampler for a model related to James–Stein estimators. Statist. Comput. 6 269–275.
  • Rosenthal, J. S. (2011). Optimal proposal distributions and adaptive MCMC. In Handbook of Markov Chain Monte Carlo (S. P. Brooks, A. Gelman, G. L. Jones and X. L. Meng, eds.). CRC Press, Boca Raton, FL.
    Mathematical Reviews (MathSciNet): MR2742422
  • 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.
    Mathematical Reviews (MathSciNet): MR2370071
    Digital Object Identifier: doi:10.1111/j.1467-9868.2007.00602.x
  • 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.
    Mathematical Reviews (MathSciNet): MR2598033
    Digital Object Identifier: doi:10.1198/jcgs.2009.08153
  • 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.). To appear.
  • Tanner, M. A. and Wong, W. H. (1987). The calculation of posterior distributions by data augmentation (with discussion). J. Amer. Statist. Assoc. 82 528–550.
    Mathematical Reviews (MathSciNet): MR898357
    Digital Object Identifier: doi:10.1080/01621459.1987.10478458
  • Tierney, L. (1994). Markov chains for exploring posterior distributions (with discussion). Ann. Statist. 22 1701–1762.
    Mathematical Reviews (MathSciNet): MR1329166
    Digital Object Identifier: doi:10.1214/aos/1176325750
    Project Euclid: euclid.aos/1176325750

Supplemental materials

  • Supplementary material: Supplementary material for “Component-Wise Markov Chain Monte Carlo: Uniform and Geometric Ergodicity Under Mixing and Composition”. This supplemental article includes all technical details and proofs for the above results.
    Digital Object Identifier: doi:10.1214/13-STS423SUPP
    Supplemental PDF (268 KB)

The Institute of Mathematical Statistics

Statistical Science

New content alerts

Email RSS ToC RSS Article
  • You have access to this content.
  • You have partial access to this content.
  • You do not have access to this content.
Turn Off MathJax

What is MathJax?

More like this

+ See more