Abstract
The aim of this contribution is to discuss approximate Bayesian computation based on the asymptotic theory of modified likelihood roots and log-likelihood ratios. Results on third-order approximations for univariate posterior distributions, also in the presence of nuisance parameters, are reviewed and the computation of asymptotic credible sets for a vector parameter of interest is illustrated. All these approximations are available at little additional computational cost over simple first-order approximations. Some illustrative examples are discussed, with particular attention to the use of matching priors.
Similar content being viewed by others
References
Barndorff-Nielsen, O.E.: Modified signed log likelihood ratio. Biometrika 78, 557–563 (1991)
Barndorff-Nielsen, O.E., Chamberlin, S.R.: Stable and invariant adjusted directed likelihoods. Biometrika 81, 485–499 (1994)
Barndorff-Nielsen, O.E., Cox, D.R.: Inference and asymptotics. Chapman and Hall, London (1994)
Brazzale, A.R., Davison, A.C., Reid, N.: Applied asymptotics. Cambridge University Press, Cambridge (2007)
Cabras, S., Ventura, L., Racugno, W.: Higher-order asymptotics for Bayesian significance tests for precise null hypotheses in the presence of nuisance parameters. Manuscript under revision (2013)
Davison, A.C.: Statistical models. Cambridge University Press, Cambridge (2003)
DiCiccio, T.J., Field, C.A., Fraser, D.A.S.: Approximations of marginal tail probabilities and inference for scalar parameters. Biometrika 77, 77–95 (1990)
DiCiccio, T.J., Martin, A.M.: Simple modifications for signed roots of likelihood ratio statistics. J. R. Stat. Soc. B 55, 305–316 (1993)
Fraser, D.A.S., Reid, N.: Strong matching of frequentist and bayesian parametric inference. J. Stat. Plan. Inference 103, 263–285 (2002)
Giummolé, F., Ventura, L.: Practical point estimation from higher-order pivots. J. Stat. Comput. Simul. 72, 419–430 (2002)
Kass, R.E., Tierney, L., Kadane, J.: Approximate methods for assessing influence and sensitivity in bayesian analysis. Biometrika 76, 663–674 (1989)
Kass, R.E., Tierney, L., Kadane, J.: The validity of posterior expansions based on Laplace’s method. In: Bayesian and likelihood methods in statistics and econometrics, pp. 473–488. Elsevier Science Publishers, North-Holland (1990)
Kharroubi, S.A., Sweeting, T.J.: Posterior simulation via the signed root log-likelihood ratio. Bayesian Anal. 5, 787–816 (2010)
Madruga, M., Pereira, C., Stern, J.: Bayesian evidence test for precise hypotheses. J. Stat. Plan. Inference 117, 185–198 (2003)
Pace, L., Salvan, A.: Adjustments of the profile likelihood from a new perspective. J. Stat. Plan. Inference 136, 3554–3564 (2006)
Pereira, C.A., Stern, J.M.: Evidence and credibility: full bayesian significance test for precise hypotheses. Entropy 1, 99–110 (1999)
Pereira, C.A., Stern, J.M., Wechslerz, S.: Can a significance test be genuinely bayesian? Bayesian Anal. 3, 79–100 (2008)
Reid, N.: Likelihood and bayesian approximation methods. Bayesian Stat. 5, 351–368 (1995)
Reid, N.: The 2000 wald memorial lectures: asymptotics and the theory of inference. Ann. Statist. 31, 1695–1731 (2003)
Reid, N., Sun, Y.: Assessing sensitivity to priors using higher order approximations. Commun. Stat. Theory Methods 39, 1373–1386 (2010)
Ruli, E., Sartori, N., Ventura, L.: Marginal posterior simulation via higher-order tail area approximations. Bayesian Anal. 9, 129–146 (2014)
Severini, T.A.: Likelihood methods in statistics. Oxford University Press, Oxford (2000)
Skovgaard, I.M.: A review of higher order likelihood inference. Bull. Int. Stat. Inst. 53, 331–351 (1989)
Skovgaard, I.M.: Scand. J. Stat. 28, 3–32 (2001)
Staicu, A.M., Reid, N.: On probability matching priors. Can. J. Stat. 36, 613–622 (2008)
Sweeting, T.J.: A framework for bayesian and likelihood approximations in statistics. Biometrika 82, 1–23 (1995)
Sweeting, T.J.: Approximate bayesian computation based on signed roots of log-density ratios (with discussion). Bayesian Stat. 5, 427–444 (1996)
Tibshirani, R.: Noninformative priors for one parameter of many. Biometrika 76, 604–608 (1989)
Tierney, L.J., Kadane, J.B.: Accurate approximations for posterior moments and marginal densities. J. Am. Stat. Assoc. 81, 82–86 (1986)
Ventura, L., Cabras, S., Racugno, W.: Prior distributions from pseudo-likelihoods in the presence of nuisance parameters. J. Am. Stat. Assoc. 104, 768–774 (2009)
Ventura, L., Ruli, E., Racugno, W.: A note on approximate bayesian credible sets based on modified log-likelihood ratios. Stat. Prob. Lett. 83, 2467–2472 (2013)
Ventura, L., Sartori, N., Racugno, W.: Objective bayesian higher-order asymptotics in models with nuisance parameters. Comput. Stat. Data Anal. 60, 90–96 (2013)
Acknowledgments
This work was supported by a grant from the University of Padua (Progetti di Ricerca di Ateneo 2011) and by the Cariparo Foundation Excellence-grant 2011/2012.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ventura, L., Reid, N. Approximate Bayesian computation with modified log-likelihood ratios. METRON 72, 231–245 (2014). https://doi.org/10.1007/s40300-014-0041-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40300-014-0041-4