NONPARAMETRIC BAYESIAN BIOASSAY WITH PRIOR CONSTRAINTS ON THE SHAPE OF THE POTENCY CURVE

We consider the problem of implementing nonparametric Bayesian analysi s of bioassay problems when the prior constrains the form of the poten cy curve (for example, to be convex, concave or ogive). Sampling based approaches to calculating posterior features of interest are detailed and illustrated. Extensions to prior constraints on hazard rates are outlined.