Sciweavers

Share
SBP
2010
Springer

Calibrating Subjective Probabilities Using Hierarchical Bayesian Models

4 years 5 months ago
Calibrating Subjective Probabilities Using Hierarchical Bayesian Models
Abstract. A body of psychological research has examined the correspondence between a judge’s subjective probability of an event’s outcome and the event’s actual outcome. The research generally shows that subjective probabilities are noisy and do not match the “true” probabilities. However, subjective probabilities are still useful for forecasting purposes if they bear some relationship to true probabilities. The purpose of the current research is to exploit relationships between subjective probabilities and outcomes to create improved, model-based probabilities for forecasting. Once the model has been trained in situations where the outcome is known, it can then be used in forecasting situations where the outcome is unknown. These concepts are demonstrated using experimental psychology data, and potential applications are discussed.
Edgar C. Merkle
Added 28 May 2010
Updated 28 May 2010
Type Conference
Year 2010
Where SBP
Authors Edgar C. Merkle
Comments (0)
books