Bayesian aggregation of two forecasts in the partial information framework

DOI10.1016/J.SPL.2016.07.018MaRDI QIDQ334027zbMATH OpenOpenAlexFDO

Authors Robin Pemantle, Philip Ernst, Ville A. Satopää, Lyle H. Ungar

Publication date 31 October 2016

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1608.04717

zbMATH Keywords

Gaussian processexpertjudgmental forecastingprobability forecast

Mathematics Subject Classification ID

Gaussian processes (60G15) Bayesian problems; characterization of Bayes procedures (62C10)

Abstract: We generalize the results of cite{SPU, SJPU} by showing how the Gaussian aggregator may be computed in a setting where parameter estimation is not required. We proceed to provide an explicit formula for a "one-shot" aggregation problem with two forecasters.

Recommendations

• The bayesian approach to the combination of forecasts: Some extensions into a Skewed environment
• Forecast combination and Bayesian model averaging: a prior sensitivity analysis
• Learning optimal forecast aggregation in partial evidence environments
• Bayesian forecast combination and Kalman filtering
• Bayesian forecast combination for VAR models
• Publication:4935406

Cites work

• scientific article; zbMATH DE number 1046392 (Why is no real title available?)
• A REDUCTION FORMULA FOR NORMAL MULTIVARIATE INTEGRALS
• Interpreted and generated signals
• Partial information framework: model-based aggregation of estimates from diverse information sources
• The Well-Calibrated Bayesian
• The bivariate normal copula

Cited in

(4)

• Partial information framework: model-based aggregation of estimates from diverse information sources
• Regularized Aggregation of One-Off Probability Predictions
• Bounds on the probability of radically different opinions
• Learning optimal forecast aggregation in partial evidence environments

This page was built for publication: Bayesian aggregation of two forecasts in the partial information framework

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q334027)