Cost-Effective Analysis

Cost-Effectiveness Analysis Methods

Investigators: Eugene Laska, Ph.D., Morris Meisner, Ph.D., Carole Siegel, Ph.D., Joseph Wanderling M.A.

PROJECT GOALS

Analysis of the cost and effectiveness of competing interventions is a common theme in many health services research projects. The generic goal of this project is the development of methodologies that enable valid statistical comparisons of interventions with respect to cost-effectiveness measures. A specific aim was to publish our statistical methods based on net health benefits (NHB) for analyzing C-E data in a scientific journal concerned with the interplay of health, economics, and statistical methodology.

RESEARCH ACTIVITIES AND RESULTS

Methods:

Both incremental cost-effectiveness ratios and net benefits have been proposed as summary measures for use in deterministic CEA. We developed a unifying proof of the optimality and equivalence of ICER-based and net benefit-based approaches to the health resource allocation problem, including both "fixed budget" and "fixed price" decision rules. If internally consistent willingness-to-pay values are used, ratio-based and net benefit-based decision rules were shown to identify the same optimal allocation. Because they have identical resource allocation implications, use of one or another of the two approaches must be based on other criteria, such as their behavior under conditions of uncertainty.
For resource allocation under a constrained budget, optimal decision ratio based rules for mutually exclusive programs require that the treatment with the highest incremental cost-effectiveness ratio (ICER) below a willingness to pay criteria (WTP) be funded. This is equivalent to determining the treatment with the smallest net health cost.

The designer of a cost-effectiveness study needs to select a sample size so that the power to reject the null hypothesis, the equality of the net health cost of two treatments, is high. In a recent paper, Briggs and Gray (1998) presented a formula under normal distribution theory that overstates sample size requirements. Using net health costs, we found simple methods for power analysis based on classical normal and on nonparametric statistical theory. We showed that much smaller sample sizes are required than was previously believed to be needed to statistically distinguish competing interventions.

Results: Under assumptions of normality, statistical methods for CEA for K treatments that mimic the deterministic rules of CEA were developed in the previous period. The objective is to determine the treatment with the maximal effectiveness whose cost per unit of effect is less than an amount l, that a decision-maker is willing to pay (WTP). This is accomplished by identifying the treatment with the statistically largest positive NHB , which is a function of l while controlling the familywise error rate both when the WTP value is given and when it is unspecified. In this period we documented the statistical procedure and prepared two papers for publication. The manuscript highlights the difference between the two error rates, one at a specific value of l, and the other , for all l. In this situation an error occurs if it occurs for at least one value of l. Both manuscripts were accepted for publication and appear in Volume 11 (2002) of Health Economics.

SIGNIFICANCE OF FINDINGS/POLICY IMPLICATIONS

We have shown that an efficient allocation of resources can be determined using decision rules based on either ICERs or on NHBs. Therefore, either analytic framework can be meaningfully applied in the economic evaluation of health interventions. This result has major implications for statistical analysis because ratios of random variables are difficult to handle and linear forms, such as net health benefit are not.

PLANS

We were unable to make progress on our plans to develop nonparametric statistical methods for comparing multiple treatments. This would extend our methods by reducing the assumptions of normality currently required. We expect to pursue this line of research during the next period.

Publications:

Laska EM, Meisner M, Siegel C (1999) . Power and sample size in cost-effectiveness analysis. Medical Decision Making, pp. 339-343.

Laska, EM, Meisner M, Siegel C, Stinnett, AA (1999). Ratio-based and net benefit-based approaches to health care resource allocation: Proofs of optimality and equivalence. Health Economics 8(2):71-4

Laska EM, Meisner M, Siegel C, Wanderling J (2002) Statistical determination of cost-effectiveness frontier based on net health benefits. Health Economics.11(3):249-264.

Meisner M, Laska EM, Siegel C, Wanderling J (2002).The familywise error rate of a simultaneous confidence band for the incremental net health benefit. Health Economics.11(3):275-280.

Project ongoing.
Updated: 5/8/00
Updated: 09/23/2002

[Top]