论文信息 - Identification and accommodation of outliers in general hierarchical models

Identification and accommodation of outliers in general hierarchical models

SUMMARY By their nature, hierarchical models involve a considerable number of structural and distributional assumptions; for example, normality and linearity are common assumptions. Considerations of robustness therefore suggest that some form of model elaboration is necessary. However, it is not clear how to achieve this in the already complex setting of hierarchical models whilst maintaining reasonable tractability in the analysis. We provide a comprehensive account of the way in which methods based on the contaminated normal niodel can be applied to the general hierarchical model, and investigate the influence of data on estimates of posterior distributions.

L. Sharples

[1] H. Scheffé. The Analysis of Variance , 1960 .

[2] R. L. Plackett,et al. The Analysis of Variance , 1960 .

[3] D. Lindley,et al. Bayes Estimates for the Linear Model , 1972 .

[4] A. O'Hagan,et al. On posterior joint and marginal modes , 1976 .

[5] Rudolf Dutter,et al. Care and Handling of Univariate Outliers in the General Linear Model to Detect Spuriosity- A , 1978 .

[6] P. Freeman. On the number of outliers in data from a linear model , 1980 .

[7] A. F. M. Smith,et al. Bayesian Approaches to Outliers and Robustness , 1983 .

[8] M. West. Outlier Models and Prior Distributions in Bayesian Linear Regression , 1984 .

[9] A Racine-Poon,et al. A Bayesian approach to nonlinear random effects models. , 1985, Biometrics.