ESTIMATING CONFIDENCE-INTERVALS FOR COST-EFFECTIVENESS RATIOS - AN EXAMPLE FROM A RANDOMIZED TRIAL

Cost-effectiveness ratios usually appear as point estimates without co nfidence intervals, since the numerator and denominator are both stoch astic and one cannot estimate the variance of the estimator exactly. T he recent literature, however, stresses the importance of presenting c onfidence intervals for cost-effectiveness ratios in the analysis of h ealth care programmes. This paper compares the use of several methods to obtain confidence intervals for the cost-effectiveness of a randomi zed intervention to increase the use of Medicaid's Early and Periodic Screening, Diagnosis and Treatment (EPSDT) programme. Comparisons of t he intervals show that methods that account for skewness in the distri bution of the ratio estimator may be substantially preferable in pract ice to methods that assume the cost-effectiveness ratio estimator is n ormally distributed. We show that non-parametric bootstrap methods tha t are mathematically less complex but computationally more rigorous re sult in confidence intervals that are similar to the intervals from a parametric method that adjusts for skewness in the distribution of the ratio. The analyses also show that the modest sample sizes needed to detect statistically significant effects in a randomized trial may res ult in confidence intervals for estimates of cost-effectiveness that a re much wider than the boundaries obtained from deterministic sensitiv ity analyses.