AN INTUITIVE MOTIVATION OF BAYESIAN BELIEF MODELS

The general use of subjective probabilities to model beliefs has been justified using many axiomatic schemes. This paper presents a rational e for probability models based on intuitive properties of belief order ings and the effect of evidence on beliefs. Qualitative probability, w hich imposes stringent constraints on belief representation schemes, i s derived from four simple assumptions about beliefs and evidence. Pro perties shown to be sufficient for the adoption of probability proper by Cox (1978) are derived here from qualitative probability and a prin ciple of plausible reasoning advanced by Polya (1954). Models based on complete orderings of beliefs extend easily to motivate set-valued re presentations of partial orderings as well.