CONFIDENCE-INTERVALS FOR COST-EFFECTIVENESS RATIOS - AN APPLICATION OF FIELLERS THEOREM

Application of cost-effectiveness analysis (CEA) is growing rapidly in health care. Two general approaches to analysis are differentiated by the type of data available: (i) deterministic models based upon secon dary analysis of retrospective data from one or more trials and other sources; and (ii) stochastic analyses in which the design of a randomi zed controlled trial is adapted to collect prospectively patient-speci fic data on costs and effectiveness. An important methodological diffe rence between these two approaches is in how uncertainty is handled. D eterministic CEA models typically rely upon sensitivity analysis to de termine the robustness of findings to alternative assumptions, whereas stochastic (CEA) analysis, as part of prospective studies, permits th e use of conventional statistical methods on the cost and effectivenes s data for both inference (hypothesis testing) and estimation. This pa per presents a procedure for the statistical analysis of cost-effectiv eness data, with specific application to those studies for which effec tiveness is measured as a binary outcome. Specifically, Fieller's Theo rem was used to calculate confidence intervals for ratios of the two r andom variables of between-treatment differences in observed costs and effectiveness, i.e. the incremental cost-effectiveness ratio.