How to do (or not to do) … Allowing for uncertainty in economic evaluations: sensitivity analysis


Limited health care budgets have emphasized the need for providers to use resources efficiently. Accordingly, there has been a rapid increase in the number of economic evaluations of communicable disease health programmes in developing countries, as there is a need to implement evidence-based policy decisions. However, given the prohibitive cost of many economic evaluations in low-income countries, interest has also been generated in pooling data and results of previously published studies. Yet, our review demonstrated that very few published economic evaluations have been performed during 1984-1997 (n=107). Certain diseases and geographical areas have also been neglected. Of those studies published, appropriate analytic techniques have been inconsistently applied. In particular, there are four immediate concerns: the narrow perspective taken-dominance of the health care provider viewpoint and reliance on intermediate outcomes measures; bias-some costs were excluded from estimates; the lack of transparency-sources of data not identified; and the absence of a critical examination of findings-many papers failed to perform a sensitivity analysis. The usefulness of previously published economic evaluations to help make resource allocation choices on an individual basis and, therefore, for the purpose of international comparisons, pooling or meta-analysis, has to be questioned in light of the results from this study. Copyright 2000 John Wiley & Sons, Ltd.


Health Policy and Planning (2001) 16 (4) 435-443 [doi:10.1093/heapol/16.4.435]

How to do (or not to do) … Allowing for uncertainty in economic evaluations: sensitivity analysis

Help us improve GOV.UK

Don’t include personal or financial information like your National Insurance number or credit card details.