Title :
Filtering information from human experts
Author :
Mendel, Max B. ; Sheridan, Thomas B.
Author_Institution :
Dept. of Mech. Eng., MIT, Cambridge, MA, USA
Abstract :
The authors propose a model, or filter, for debiasing opinions from multiple experts and combining them into a single consistent estimate of some variable of interest. A distinguishing feature of the approach consists of making the calibration of experts an integral part of filtering. This enables the filter to learn from previous experience with the experts. The theoretical development takes a Bayesian perspective, using B. de Finetti´s notion of exchangeability (1964). Experimental results with a preliminary computer implementation of the filter show that its estimates are better than those from comparable filters that do not involve calibration
Keywords :
Bayes methods; filtering and prediction theory; knowledge engineering; learning systems; Bayesian perspective; computer implementation; exchangeability; expert calibration; human experts; information filtering; learning; opinion combination; opinion debiasing; Bayesian methods; Calibration; Displays; Electrical equipment industry; Humans; Industrial control; Information filtering; Information filters; Man machine systems; Supervisory control;
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
