The irrelevance of inference: a decision-making approach to the stochasticevaluation of health care technologies

The literature which considers the statistical properties of cost-effective ness analysis has focused on estimating the sampling distribution of either an incremental cost-effectiveness ratio or incremental net benefit for cla ssical inference. However, it is argued here that rules of inference are ar bitrary and entirely irrelevant to the decisions which clinical and economi c evaluations claim to inform. Decisions should be based only on the mean n et benefits irrespective of whether differences are statistically significa nt or fall outside a Bayesian range of equivalence. Failure to make decisio ns in this way by accepting the arbitrary rules of inference will impose co sts which can be measured in terms of resources or health benefits forgone. The distribution of net benefit is only relevant to deciding whether more information is required. A framework for decision making and establishing t he value of additional information is presented which is consistent with th e decision rules in CEA. This framework can distinguish the simultaneous bu t conceptually separate steps of deciding which alternatives should be chos en, given existing information, from the question of whether more informati on should be acquired. It also ensures that the type of information acquire d is driven by the objectives of the health care system, is consistent with the budget constraint on service provision and that research is designed e fficiently. (C) 1999 Elsevier Science B.V. All rights reserved. JEL classif ication: I18.