Abstract:
|
Subjective Bayesian prior distributions elicited from experts can be aggregated together to form group priors. This can be achieved using mathematical aggregation rules, or behavioural aggregation methods which allow experts to form a consensus distribution together. Under the context of a clinical trial design, we compare the mathematical Equal Weight aggregation, and the behavioural Classical Method and Sheffield Elicitation Framework. The individual experts’ and the aggregated distributions are compared using proper scoring rules to comment on the informativeness and calibration of the distributions. The three aggregation methods outperform the individual experts, and the Sheffield Elicitation Framework performs best amongst them.
|