The Need for Adding Judgment in Bayesian Prediction

摘要

There are many examples of successful application of the famous Bayes' theorem to forecast the outcome of causes or influences of events. However, there are also many examples of failures of just using probabilities and statistics without also using judgments in each particular application. This is particularly true in medical diagnoses and in sports. The extension we proposed found a way to calculate probabilities combining logical inference of data and judgment. This research extends the use of Bayes' theorem by incorporating judgments within the framework of the frequently used decision theory, the analytic network process (ANP) and illustrates its use with an application.