Bayesian analysis of outliers via akaike's predictive likelihood of a model

DOI10.1080/03610918408812361zbMath0565.62016OpenAlexW2029905854MaRDI QIDQ3680066

Genshiro Kitagawa

Publication date: 1984

Published in: Communications in Statistics - Simulation and Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/03610918408812361

zbMATH Keywords

outliersindependent observationsnormal populationsAICpredictive likelihoodunknown variancerobust estimatemean shiftunknown meansposterior probabilitiesprior probabilitiesexpected log likelihooddominant populationquasi-Bayesian procedure

Mathematics Subject Classification ID

Bayesian inference (62F15) Robustness and adaptive procedures (parametric inference) (62F35)

Related Items

Quasi-Bayesian modelling of multivariate outliers, Bayesian inference in life tests based on exponential model with outliers when sample size is a random variable, A quasi-Bayesian analysis of regression outliers using Akaike's predictive likelihood, Genetic algorithms for outlier detection in multiple regression with different information criteria, Quasi-Bayesian estimation of Stigler's data sets

Cites Work

• Unnamed Item
• Unnamed Item
• On the use of the predictive likelihood of a Gaussian model
• A quasi Bayesian approach to outlier detection
• Linear Models and Spurious Observations
• Posterior probabilities for choosing a regression model
• A special property of the expected log likelihooda special property of the expected log likelihood
• A Bayesian approach to some outlier problems