Abstract
The sensitivity of posterior inferences to model specification can be considered as an indicator of the presence of outliers, that are to be considered as highly unlikely values under the assumed model. The occurrence of anomalous values can seriously alter the shape of the likelihood function and lead to posterior distributions far from those one would obtain without these data inadequacies. In order to deal with these hindrances, a robust approach is discussed, which allows us to obtain outliers’ resistant posterior distributions with properties similar to those of a proper posterior distribution. The methodology is based on the replacement of the genuine likelihood by a weighted likelihood function in the Bayes’ formula.
Similar content being viewed by others
References
Agostinelli C (2002) Robust model selection in regression via weighted likelihood methodology. Stat Probab Lett 56: 289–300
Agostinelli C (2006) Notes on pearson residuals and weighted likelihood estimating equations. Stat Probab Lett 76: 1930–1934
Agostinelli C (2009) Estimating the model of the majority of the data. Adv Appl Math Sci 1: 209–227
Agostinelli C, Alqallaf F (2010) Robust inference in generalized linear models. http://www.dst.unive.it/~claudio/index.php/research/publications
Agostinelli C, Markatou M (2001) Test of hypothesis based on the weighted likelihood methodology. Stat Sinica 1: 499–514
Barnett V, Toby L (1994) Outliers in statistical data. Wiley, New York
Basu A, Lindsay B (1994) Minimum disparity estimation for continuous models: efficiency, distributions and robustness. Ann Inst Stat Math 46: 683–705
Berger J (1994) An overview of robust bayesian analysis (with discussion). Test 3: 5–124
Box G, Tiao G (1962) A further look at robustness via bayes’s theorem. Biometrika 49: 419–432
Cressie N, Read T (1984) Multinomial goodness-of-fit tests. J R Stat Soc Ser B 46: 440–464
Cressie N, Read T (1988) Cressie–Read statistic. In: Kotz S, Johnson NL (eds) Encyclopedia of statistical sciences, supplementary volume. Wiley, pp 37–39.
Dawid A (1973) Posterior expectations for large observations. Biometrika 60: 664–667
Field C, Smith B (1995) Robust estimation—a weighted maximum likelihood approach. Int Stat Rev 62: 405–424
Gelman A, Carlin J, stern H, Rubin D (2004) Bayesian data analysis. Chapman and Hall/CRC, Boca Raton
Greco L, Racugno W, Ventura L (2008) Robust likelihood functions in bayesian analysis. J Stat Plan Inf 138: 1258–1270
Hampel F, Ronchetti E, Rousseeuw P, Stahel W (1986) Robust statistics. The approach based on influence functions. Wiley, New York
Hu F, Zidek J (2002) The weighted likelihood. Can J Stat 30: 347–371
Huber P, Ronchetti E (2009) Robust statistics. 2nd edn. Wiley, New Jersey
Kass R, Raftery A (1995) Bayes factors. J Am Stat Assoc 90: 773–795
Lavine M (1991) Sensitivity in bayesian statistics: the prior and the likelihood. J Am Stat Assoc 86: 396–399
Lazar N (2003) Bayesian empirical likelihood. Biometrika 90: 319–326
Length R, Green P (1987) Consistency of deviance-based m-estimators. J R Stat Soc B 49: 326–330
Lindsay B (1994) Efficiency versus robustness: the case for minimum hellinger distance and related methods. Ann Stat 22: 1018–1114
Markatou M, Basu A, Lindsay B (1997) Weighted likelihood estimating equations: the discrete case with applications to logistic regression. J Stat Plan Inf 57: 215–232
Markatou M, Basu A, Lindsay B (1998) Weighted likelihood estimating equations with a bootstrap root search. J Am Stat Assoc 93: 740–750
Maronna A, Martin R, Yohai V (2006) Robust statistics. Theory and methods. Wiley, Chichester
Monahan J, Boos D (1992) Proper likelihoods for bayesian analysis. Biometrika 79: 271–278
Neykov N, Neytchev P (1990) A robust alternative of the maximum likelihood estimators. In: Proceedings of COMPSTAT 1990, pp 99–100
O’Hagan A (1979) On outlier rejection phenomena in bayes inference. J R Stat Soc B 41: 258–367
O’Hagan A (1988) Modelling with heavy tails. BayesStat3. pp 345–359
O’Hagan A (1990) Outliers and credence for location parameter inference. J Am Stat Assoc 85: 172–176
Park C, Basu A, Lindsay B (2002) The residual adjustment function and weighted likelihood: a graphical interpretation of robustness of minimum disparity estimators. Comput Stat Data Anal 39(1): 21–33
Pericchi L, Perez M (1994) Posterior robustness with more than one sampling model. J Stat Plan Inf 40: 279–294
Prakasa Rao B (1983) Nonparametric functional estimation. Academic Press, New York
R Development Core Team (2010) R: a language and environment for statistical computing. R foundation for statistical computing, Vienna, Austria. http://www.R-project.org, ISBN 3-900051-07-0
Shyamalkumar N (2000) Robust Bayesian analysis. Springer, Berlin
Windham M (1995) Robustifying model fitting. J R Stat Soc B 57: 599–609
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Agostinelli, C., Greco, L. A weighted strategy to handle likelihood uncertainty in Bayesian inference. Comput Stat 28, 319–339 (2013). https://doi.org/10.1007/s00180-011-0301-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-011-0301-1