A Bayesian approach to parallel line bioassay
This paper considers parallel line bioassay from a Bayesian point of view. The mathematical formulation considered is a nonlinear one in which the log potency ratio appears explicitly as a parameter. Models for estimating log potency ratio from a single assay, and also for combining information from several assays are discussed. The method of analysis follows closely the ideas of Lindley & Smith (1972) for the linear model. © 1980 Biometrika Trust.