Bayesian model averaging: A systematic review and conceptual classification
arXiv:1509.08864 · doi:10.1111/insr.12243
Abstract
Bayesian Model Averaging (BMA) is an application of Bayesian inference to the problems of model selection, combined estimation and prediction that produces a straightforward model choice criteria and less risky predictions. However, the application of BMA is not always straightforward, leading to diverse assumptions and situational choices on its different aspects. Despite the widespread application of BMA in the literature, there were not many accounts of these differences and trends besides a few landmark revisions in the late 1990s and early 2000s, therefore not taking into account any advancements made in the last 15 years. In this work, we present an account of these developments through a careful content analysis of 587 articles in BMA published between 1996 and 2014. We also develop a conceptual classification scheme to better describe this vast literature, understand its trends and future directions and provide guidance for the researcher interested in both the application and development of the methodology. The results of the classification scheme and content review are then used to discuss the present and future of the BMA literature.
References in corpus (2)
Cited by in corpus (24)
- Phenomenological constraints on the transport properties of QCD matter with data-driven model averaging
- ACCESS: A featureless optical transmission spectrum for WASP-19b from Magellan/IMACS
- A review of predictive uncertainty estimation with machine learning
- ARIADNE: Measuring accurate and precise stellar parameters through SED fitting
- Fusion of Probability Density Functions
- Get on the BAND Wagon: A Bayesian Framework for Quantifying Model Uncertainties in Nuclear Dynamics
- Forming intracluster gas in a galaxy protocluster at a redshift of 2.16
- Footprint of publication selection bias on meta-analyses in medicine, environmental sciences, psychology, and economics
- Four-of-a-kind? Comprehensive atmospheric characterisation of the HR 8799 planets with VLTI/GRAVITY
- Setting the stage for the search for life with the Habitable Worlds Observatory: Properties of 164 promising planet survey targets
- Improved information criteria for Bayesian model averaging in lattice field theory
- A multi-model ensemble Kalman filter for data assimilation and forecasting
- Bayesian quantification of strongly-interacting matter with color glass condensate initial conditions
- Accelerating Multi-Model Bayesian Inference, Model Selection and Systematic Studies for Gravitational Wave Astronomy
- CRPS Learning
- Feeding and feedback processes in the Spiderweb proto-intracluster medium
- Bayesian fitting of multi-Gaussian expansion models to galaxy images
- Assessing inter-rater reliability with heterogeneous variance components models: Flexible approach accounting for contextual variables
- Informed Bayesian survival analysis
- Bayesian model mixing with multi-reference energy density functional
- Dynamical masses of young stellar objects with the VLBA: DYNAMO-VLBA: Radio binary stars in Orion
- Automating Model Comparison in Factor Graphs
- Achieving Skilled and Reliable Daily Probabilistic Forecasts of Wind Power at Subseasonal-to-Seasonal Timescales over France
- An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism