Bayesian Model Averaging: A Tutorial

By Jennifer A. Hoeting, David Madigan, Adrian E. Raftery, C. Volinsky. 2016

3,317 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning stable and predictive structures in kinetic systems (2018, methodology): “The ranking we propose is similar to Bayesian model averaging (BMA) (31) and is based on how often each variable appears in a top-ranked model.”
Obtaining Well Calibrated Probabilities Using Bayesian Binning (2015, positive): “However , model averaging is typically superior to model selection (Hoeting et al. 1999).”
A Bayesian approach to climate model evaluation and multi‐model averaging with an application to global mean surface temperatures from IPCC AR4 coupled climate models (2006, methodology): “This method is called Bayesian model averaging (BMA) [Hoeting et al., 1999].”
A guide to group effective connectivity analysis, part 2: Second level analysis with PEB (2019, methodology): “This is the average of the parameters from different models, weighted by the models’ posterior probabilities (Hoeting et al., 1999; Penny et al., 2006).”
Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriors (2020, background): “This α k weighting can be interpreted as Bayesian model averaging (BMA; Madigan et al., 1996; Hoeting et al., 1999) on a discrete model space where model k has posterior density p k ( θ | y ).”
Neural Decision Trees (2017, methodology): “The model evidence is given by look for a review in Hoeting et al. (1999).”
Variance-based global sensitivity analysis for multiple scenarios and models with implementation using sparse grid collocation (2015, methodology): “The first and second term at the right hand side of the equations are termed as within-model variance and between-model variance, respectively (Draper, 1995; Hoeting et al., 1999).”
The JASP guidelines for conducting and reporting a Bayesian analysis (2019, unknown): “…for a parameter accounts for both the uncertainty about the parameter within any one model and the uncertainty about the model itself, providing an estimate of the parameter that is a compromise between the candidate models (for more details see Hoeting, Madigan, Raftery, & Volinsky, 1999).”
Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC (2015, methodology): “After ﬁtting a Bayesian model we often want to measure its predictive accuracy, for its own sake or for purposes of model comparison, selection, or averaging (Geisser and Eddy, 1979, Hoeting et al., 1999, Vehtari and Lampinen, 2002, Ando and Tsay, 2010, Vehtari and Ojanen, 2012).”
SHRINKAGE, PRETEST AND ABSOLUTE PENALTY ESTIMATORS IN PARTIALLY LINEAR MODELS (2007, unknown): “Remark Note that the Steinian strategy is similar in spirit to the model-averaging procedures, Bayesian or otherwise; see Bickel (1984), Hoeting et al. (1999, 2002) and Burnham & Anderson (2002).”