Representing human uncertainty by subjective likelihood estimates

We give a definition of human uncertainty through subjective likelihood estimates. The subject is asked for his estimated likelihood of different statements, given a present piece of observation. With this interpretation of human uncertainty, we are able to perform consistent inference about our target variables, by formally treating the input as likelihood factors. By focusing on likelihood estimates given the present observation only, we eliminate the problem of handling the subject's overall judgement. The algorithm has been successfully implemented in an expert system for classification of wildwood mushrooms.