Global and Local Robustness Approaches: Uses and Limitations

We provide a comparative review of the global and local approaches to Bayesian robustness. Here, we focus on the issue of assessing robustness on a (more) practical level. Specifically, we address the issues of interpretation, calibration, and the limitations of these measures. The important issue of how one may proceed with a follow-up investigation, when robustness is found to be lacking, is also reviewed, including how both the global and local robustness measures, together, can be useful in such a follow-up study. We then briefly summarize the asymptotics, and end with a discussion.

[1]  Joel B. Greenhouse,et al.  [Investigating Therapies of Potentially Great Benefit: ECMO]: Comment: A Bayesian Perspective , 1989 .

[2]  Paul H. Garthwaite,et al.  Elicitation of Prior Distributions for Variable-Selection Problems in Regression , 1992 .

[3]  Adrian F. M. Smith,et al.  Bayesian Statistics 5. , 1998 .

[4]  James O. Berger,et al.  Robust Bayesian analysis of selection models , 1998 .

[5]  David Ríos Insua,et al.  Robust Bayesian analysis , 2000 .

[6]  James O. Berger,et al.  Bayesian robustness in bidimensional models: Prior independence , 1994 .

[7]  Joseph B. Kadane,et al.  Robustness of Bayesian analyses , 1984 .

[8]  James O. Berger,et al.  Robust Bayesian analysis of the binomial empirical Bayes problem , 1993 .

[9]  J. Ware Investigating Therapies of Potentially Great Benefit: ECMO , 1989 .

[10]  L. Wasserman,et al.  Bayesian Inference with Specified Prior Marginals , 1991 .

[11]  A likelihood based robust Bayesian summary , 1999 .

[12]  E. Moreno,et al.  Bayesian robustness for hierarchical ε-contamination models , 1993 .

[13]  E. Moreno Global Bayesian Robustness for Some Classes of Prior Distributions , 2000 .

[14]  James O. Berger,et al.  Applications and Limitations of Robust Bayesian Bounds and Type II MLE , 1994 .

[15]  Paul Gustafson,et al.  Local Robustness in Bayesian Analysis , 2000 .

[16]  Wayne S. Smith,et al.  Interactive Elicitation of Opinion for a Normal Linear Model , 1980 .

[17]  D. Insua,et al.  Bayesian Forecasting for Accident Proneness Evaluation , 1999 .

[18]  Siva Sivaganesan,et al.  Range of posterior measures for priors with arbitrary contaminations , 1988 .