Theory of Probability and Mathematical Statistics
Non-informative bayesian inference for heterogeneity in a generalized marginal random effects meta-analysis]
O. Bodnar
Download PDF
Abstract: In this paper an objective Bayesian inference is proposed for the heterogeneity parameter in a generalized marginal random effects model. Models of this kind are widely used in meta-analysis and in inter-laboratory comparisons. Under the assumption of elliptically contoured distributions, a reference prior for the model parameters is obtained and the analytical expression of the corresponding posterior is derived. We also state necessary conditions for the resulting posterior to be proper and for the existence of its first two moments. The obtained general theoretical results are illustrated for three popular families of elliptically contoured distributions: normal distribution, t-distribution, and Laplace distribution.
Keywords: Non-informative prior, generalized random effects model, meta-analysis, estimation of heterogeneity, elliptically contoured distribution.
Bibliography: 1.G. Andrews, R. Askey, R. Roy, Special functions, Cambridge University Press, Cambridge, 2000.
2. J. Berger, J. M. Bernardo, On the development of reference priors, Bayesian Statistics (J. M. Bernardo, J. Berger, A. P. Dawid, A. F. M. Smith, eds.), vol. 4, Oxford University Press, Oxford, 1992, 35–60.
3. O. Bodnar, C. Elster, Analytical derivation of the reference prior by sequential maximization of shannon’s mutual information in the multi-group parameter case, Journal of Statistical Planning and Inference, 147 (2014), 106–116.
4. O. Bodnar, C. Elster, J. Fischer, A. Possolo, B. Toman, Evaluation of uncertainty in the adjustment of fundamental constants, Metrologia, 53 (2016), S46–S54.
5. O. Bodnar, A. Link, B. Arendacká, A. Possolo, C. Elster, Bayesian estimation in random effects meta-analysis using a non-informative prior, Statistics in Medicine, 36 (2017), no. 2, 378–399.
6. O. Bodnar, A. Link, C. Elster, Objective Bayesian inference for a generalized marginal random effects model, Bayesian Analysis, 11 (2016), 25–45.
7. Y. Chung, S. Rabe-Hesketh, I.-H. Choi, Avoiding zero between-study variance estimates in random-effects meta-analysis, Statistics in Medicine, 32 (2013), no. 23, 4071–4089.
8. C. Combescure, Y. Foucher, D. Jackson, Meta-analysis of single-arm survival studies: A distribution-free approach for estimating summary survival curves with random effects, Statistics in Medicine, 33 (2014), no. 15, 2521–2537.
9. R. DerSimonian, N. Laird, Meta-analysis in clinical trials, Controlled Clinical Trials, 7 (1986), no. 3, 177–188.
10. C. Elster, B. Toman, Analysis of key comparison data: critical assessment of elements of current practice with suggested improvements, Metrologia, 50 (2013), no. 5, 549.
11. T. Eltoft, T. Kim, T.-W. Lee, On the multivariate Laplace distribution, IEEE Signal Processing Letters, 13 (2006), 300–303.
12. M. Evans, T. Swartz, Approximating integrals via monte carlo and deterministic methods, Oxford University Press, New York, 2000.
13. A. Gelman, Prior distributions for variance parameters in hierarchical models, Bayesian Analysis, 1 (2006), 515–533.
14. E. Gómez, M. A. Gómez-Villegas, J. M. Marı́n, A survey on continuous elliptical vector distributions, Revista Matemática Complutense, 16 (2003), 345–361.
15. A. Guolo, C. Varin, Random-effects meta-analysis: the number of studies matters, Statistical Methods in Medical Research, 26 (2017), no. 3, 1500–1518.
16. A. Gupta, T. Varga, T. Bodnar, Elliptically contoured models in statistics and portfolio theory, Springer, New York, 2013.
17. R. J. Hardy, S. G. Thompson, A likelihood approach to meta-analysis with random effects, Statistics in Medicine, 15 (1996), no. 6, 619–629.
18. D. A. Harville, Bayesian inference for variance components using only error contrasts, Biometrika, 61 (1974), no. 2, 383–385.
19. M. Henmi, J. B. Copas, Confidence intervals for random effects meta-analysis and robustness to publication bias, Statistics in Medicine, 29 (2010), no. 29, 2969–2983.
20. J. Higgins, S. G. Thompson, D. J. Spiegelhalter, A re-evaluation of random-effects meta-analysis, Journal of the Royal Statistical Society: Series A (Statistics in Society), 172 (2009), no. 1, 137–159.
21. J. Higgins, A. Whitehead, Borrowing strength from external trials in a meta-analysis, Statistics in Medicine, 15 (1996), no. 24, 2733–2749.
22. H. Jeffreys, An invariant form for the prior probability in estimation problems, Proceedings of the Royal Society A, 186 (1946), 453–461.
23. N. Klein, T. Kneib, Scale-dependent priors for variance parameters in structured additive distributional regression, Bayesian Analysis, 11 (2016), no. 4, 1071–1106.
24. G. Knapp, J. Hartung, Improved tests for a random effects meta-regression with a single covariate, Statistics in Medicine, 22 (2003), no. 17, 2693–2710.
25. P. C. Lambert, A. J. Sutton, P. R. Burton, K. R. Abrams, D. R. Jones, How vague is vague? A simulation study of the impact of the use of vague prior distributions in MCMC using WinBUGS, Statistics in Medicine, 24 (2005), no. 15, 2401–2428.
26. P. S. Laplace, Théorie analitique des probabilités, Courcier, Paris, 1812.
27. J. Mandel, R. Paule, Interlaboratory evaluation of a material with unequal numbers of replicates, Analytical Chemistry, 42 (1970), no. 11, 1194–1197.
28. J. Mandel, R. Paule, Correction — interlaboratory evaluation of a material with unequal numbers of replicates, Analytical Chemistry, 43 (1971), no. 10, 1287–1287.
29. P. J. Mohr, B. N. Taylor, D. B. Newell, Codata recommended values of the fundamental physical constants: 2010, Reviews of Modern Physics, 84 (2012), 1527–1605.
30. P. W. Novianti, K. C. B. Roes, I. van der Tweel, Estimation of between-trial variance in sequential meta-analyses: A simulation study, Contemporary Clinical Trials, 37 (2014), no. 1, 129–138.
31. D. I. Ohlssen, L. D. Sharples, D. J. Spiegelhalter, Flexible random-effects models using Bayesian semi-parametric models: Applications to institutional comparisons, Statistics in Medicine, 26(2007), no. 9, 2088–2112.
32. R. C. Paule, J. Mandel, Consensus values and weighting factors, Journal of Research of the National Bureau of Standards, 87 (1982), no. 5, 377–385.
33. E. M. Pullenayegum, An informed reference prior for between-study heterogeneity in meta-analyses of binary outcomes, Statistics in Medicine, 30 (2011), no. 26, 3082–3094.
34. C. P. Robert, G. Casella, Monte carlo statistical methods, 2 ed., New York: Springer, 2004.
35. A. L. Rukhin, Estimating heterogeneity variance in meta-analysis, Journal of the Royal Statistical Society: Series B, 75 (2013), 451–469.
36. K. Sidik, J. N. Jonkman, Simple heterogeneity variance estimation for meta-analysis, Journal of the Royal Statistical Society: Series C (Applied Statistics), 54 (2005), no. 2, 367–384.
37. D. Simpson, H. Rue, A. Riebler, T. G. Martins, S. H. Sørbye, Penalising model component complexity: A principled, practical approach to constructing priors, Statistical Science, 32(2017), no. 1, 1–28.
38. T. C. Smith, D. J. Spiegelhalter, A. Thomas, Bayesian approaches to random-effects meta-analysis: A comparative study, Statistics in Medicine, 14 (1995), no. 24, 2685–2699.
39. A. J. Sutton, J. Higgins, Recent developments in meta-analysis, Statistics in Medicine, 27(2008), 625–650.
40. R. M. Turner, J. Davey, M. J. Clarke, S. G. Thompson, J. Higgins, Predicting the extent of heterogeneity in meta-analysis, using empirical data from the Cochrane Database of Systematic Reviews, International Journal of Epidemiology, 41 (2012), no. 3, 818–827.
41. R. M. Turner, D. Jackson, Y. Wei, S. G. Thompson, J. Higgins, Predictive distributions for between-study heterogeneity and simple methods for their application in Bayesian meta-analysis, Statistics in Medicine, 34 (2015), 984–998.
42. D. E. Warn, S. G. Thompson, D. J. Spiegelhalter, Bayesian random effects meta-analysis of trials with binary outcomes: methods for the absolute risk difference and relative risk scales, Statistics in Medicine, 21 (2002), no. 11, 1601–1623.
