|
Paired repeated measures are commonly used to demonstrate the system equivalency of different measures up to a pre-specified threshold. For example, for the oxymetry comparison study that motivates our research, FDA has clear guidelines regarding a pulse oximeter as approvable via testing the root mean squares (RMS), a composite measure of both mean and variance parameters. For this composite test, existing methods have been either ad hoc or relying on crude large-sample approximation with unsatisfactory performance.
We develop a novel generalized pivotal test approach to rigorously and accurately establishing the system equivalency via testing the RMS. The proposed methods have well-controlled type I errors and favorable performance in our extensive numerical studies.
When analyzing data from an oxymetry comparison study, conducted by a medical device company to demonstrate performance equivalency between a FDA-cleared oxymetry system and an investigational system, our proposed method resulted in a more significant p-value to support the system equivalency, in comparison to the existing method.
|
