AGGREGATING POINT ESTIMATES - A FLEXIBLE MODELING APPROACH

In many decision situations information is available from a number of different sources. Aggregating the diverse bits of information is an i mportant aspect of the decision-making process but entails special sta tistical modeling problems in characterizing the information. Prior re search in this area has relied primarily on the use of historical data as a basis for modeling the information sources. We develop a Bayesia n framework that a decision maker can use to encode subjective knowled ge about the information sources in order to aggregate point estimates of an unknown quantity of interest. This framework features a highly flexible environment for modeling the probabilistic nature and interre lationships of the information sources and requires straightforward an d intuitive subjective judgments using proven decision-analysis assess ment techniques. Analysis of the constructed model produces a posterio r distribution for the quantity of interest. An example based on healt h risks due to ozone exposure demonstrates the technique.