Abstract

There was a time when a simple dichotomy characterized any health economic evaluations. On the one hand there were those economic appraisals that were conducted alongside clinical trials and which commonly employed statistical methods in so-called stochastic evaluations. On the other, there was the use of decision analytic modeling to synthesize data from secondary sources in order to estimate cost-effectiveness in a deterministic fashion. Now, however, the distinctions are becoming ever more blurred. The limitations of single trials as the sole vehicle for economic appraisal is widely reported and, in particular, the continued need for modeling to adapt trial-based analyses is well understood. Furthermore, the use of probabilistic sensitivity analysis to represent uncertainty in modeling studies offers the opportunity to make statistical statements about the impact of parameter uncertainty for cost-effectiveness estimates from deterministic models.