Conditional Degree of Belief

This paper articulates and defends a suppositional interpretation of conditional degree of belief. First, I focus on a type of probability that has a crucial role in Bayesian inference: conditional degrees of belief in an observation, given a statistical hypothesis. The suppositional analysis explains, unlike other accounts, why these degrees of belief track the corresponding probability density functions. Then, I extend the suppositional analysis and argue that all probabilities in Bayesian inference should be understood suppositionally and model-relative. This sheds a new and illuminating light on chance-credence coordination principles, the relationship between Bayesian models and their target system, and the epistemic significance of Bayes' Theorem