A bayesian semi-parametric approach for cost-effectiveness analysis in health economics

We consider the problem of assessing new and existing technologies for their cost-effectiveness in the case where data on both costs and efficacy are available from a clinical trial, and we address it by means of the cost-effectiveness acceptability curve in the simple case where efficacy is measured as a binary outcome. We consider a Bayesian approach, and in recognising that cost data usually exhibit highly skew, heavy-tailed and, possibly multi-modal distributions, we introduce a model for costs composed of a piecewise constant density up to an unknown endpoint, and a generalised Pareto distribution for the remaining tail.