Computational Statistics

, Volume 32, Issue 1, pp 51–69 | Cite as

Bayesian inference using a noninformative prior for linear Gaussian random coefficient regression with inhomogeneous within-class variances

  • Clemens Elster
  • Gerd Wübbeler
Original Paper


A Bayesian inference for a linear Gaussian random coefficient regression model with inhomogeneous within-class variances is presented. The model is motivated by an application in metrology, but it may well find interest in other fields. We consider the selection of a noninformative prior for the Bayesian inference to address applications where the available prior knowledge is either vague or shall be ignored. The noninformative prior is derived by applying the Berger and Bernardo reference prior principle with the means of the random coefficients forming the parameters of interest. We show that the resulting posterior is proper and specify conditions for the existence of first and second moments of the marginal posterior. Simulation results are presented which suggest good frequentist properties of the proposed inference. The calibration of sonic nozzle data is considered as an application from metrology. The proposed inference is applied to these data and the results are compared to those obtained by alternative approaches.


Random coefficient regression Bayesian inference Noninformative prior 



The authors thank the referees for helpful comments and suggestions, and Bodo Mickan (PTB) for providing the sonic nozzle calibration data.


  1. Berger J, Bernardo JM (1992) Reference priors in a variance components problem. In: Goel P (ed) Bayesian analysis in statistics and econometrics. Lecture notes in statistics, vol 75. Springer, New York, pp 177–194CrossRefGoogle Scholar
  2. Berger J, Bernardo JM (1992c) On the development of reference priors. In: Bernardo JM, Berger J, Dawid AP, Smith AFM (eds) Bayesian statistics, vol 4. University Press, Oxford, pp 35–60Google Scholar
  3. Berger J, Sun D (2008) Objective priors for the bivariate normal model. Ann Stat 36(2):963–982MathSciNetCrossRefMATHGoogle Scholar
  4. Berger J, Bernardo JM, Sun D (2009) The formal definition of reference priors. Ann Stat 37(5):905–938MathSciNetCrossRefMATHGoogle Scholar
  5. Bodnar O, Elster C (2014) Analytical derivation of the reference prior by sequential maximization of shannon’s mutual information in the multi-group parameter case. J Stat Plan Inference 147:106–116MathSciNetCrossRefMATHGoogle Scholar
  6. Bodnar O, Link A, Elster C (2016) Objective Bayesian inference for a generalized marginal random effects model. Bayesian Anal 11(1):25–45MathSciNetCrossRefGoogle Scholar
  7. Browne WJ, Draper D (2006) A comparison of Bayesian and likelihood-based methods for fitting multilevel models. Bayesian Anal 1(3):473–514MathSciNetMATHGoogle Scholar
  8. Clarke B, Yuan A (2004) Partial information reference priors: derivation and interpretations. J Stat Plan Inference 123(2):313–345MathSciNetCrossRefMATHGoogle Scholar
  9. Daniels MJ (1999) A prior for the variance in hierarchical models. Can J Stat 27(3):567–578MathSciNetCrossRefMATHGoogle Scholar
  10. Datta GS, Ghosh M (1995) Some remarks on noninformative priors. J Am Stat Assoc 90(432):1357–1363MathSciNetCrossRefMATHGoogle Scholar
  11. Datta GS, Ghosh M (1996) On the invariance of noninformative priors. Ann Stat 24:141–159MathSciNetCrossRefMATHGoogle Scholar
  12. Datta GS, Smith DD (2003) On propriety of posterior distributions of variance components in small area estimation. J Stat Plan Inference 112:175–183MathSciNetCrossRefMATHGoogle Scholar
  13. Foulley JL, San Cristobal M, Gianola D, Im S (1992) Marginal likelihood and Bayesian approaches to the analysis of heterogeneous residual variances in mixed linear Gaussian models. Comput Stat Data An 13(3):291–305CrossRefMATHGoogle Scholar
  14. Gelman A (2006) Prior distributions for variance parameters in hierarchical models. Bayesian Anal 1:515–533MathSciNetCrossRefMATHGoogle Scholar
  15. Hobert JP, Casella G (1996) The effect of improper priors on Gibbs sampling in hierarchical linear mixed models. J Am Stat Assoc 91(436):1461–1473. doi: 10.1080/01621459.1996.10476714 MathSciNetCrossRefMATHGoogle Scholar
  16. Lütkepohl H (1996) Handbook of matrices, 1st edn. Wiley, New YorkMATHGoogle Scholar
  17. McCulloch CE, Searle SR (2008) Generalized, linear, and mixed models, 2nd edn. Wiley, New YorkMATHGoogle Scholar
  18. Pinheiro JC, Bates DM (2000) Mixed-effects models in S and S-PLUS. Springer, BerlinCrossRefMATHGoogle Scholar
  19. Pretorius AL, Van Der Merwe AJ (2002) Reference and probability-matching priors in Bayesian analysis of mixed linear models. J Anim Breed Genet 119(5):311–324CrossRefGoogle Scholar
  20. Robert CP, Casella G (2004) Monte Carlo statistical methods, 2nd edn. Springer, New YorkCrossRefMATHGoogle Scholar
  21. Searle SR, Casella G, McCulloch CE (1992) Variance components. Wiley, New YorkCrossRefMATHGoogle Scholar
  22. Sun D, Tsutakawa RK, He Z (2001) Propriety of posteriors with improper priors in hierarchical linear mixed models. Stat Sin 11:77–95MathSciNetMATHGoogle Scholar
  23. Tsai MY, Hsiao CK (2008) Computation of reference Bayesian inference for variance components in longitudinal studies. Comput Stat 23(4):587–604MathSciNetCrossRefMATHGoogle Scholar
  24. Wand MP (2007) Fisher information for generalised linear mixed models. J Multivar Anal 98(7):1412–1416MathSciNetCrossRefMATHGoogle Scholar
  25. Wright J, Mickan B, Paton R, Park KA, Si Nakao, Chahine K, Arias R (2007) CIPM key comparison for low-pressure gas flow: CCM. FF-K6. Metrologia 44(1A):07,008CrossRefGoogle Scholar
  26. Yang R, Berger J (1997) A catalog of noninformative priors. Technical report. Duke University, ISDS 97–42Google Scholar
  27. Yang R, Chen MH (1995) Bayesian analysis for random coefficient regression models using noninformative priors. J Multivar Anal 55:283–311MathSciNetCrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Physikalisch-Technische Bundesanstalt (PTB)BerlinGermany

Personalised recommendations