Tradeoff studies help designers better understand how different design considerations relate to one another and to make decisions. Generally a tradeoff study involves a systematic multi-criteria evaluation of various alternatives for a particular system or subsystem. After evaluating these alternatives, designers eliminate those that perform poorly using the Pareto dominance criterion and explore more carefully those that remain.
An analogous procedure is possible when design criteria are uncertain. This approach is based on stochastic dominance principles that involve comparisons of probability distributions defined in the design criteria space. Although this is well-founded mathematically, the procedure can be computationally expensive because it typically entails a sampling-based uncertainty propagation method (e.g. Monte Carlo or quasi-Monte Carlo methods) for each alternative being considered.
In this paper we describe a statistically sound method which allows designers to sample the minimum number of samples necessary to eliminate dominated design alternatives under uncertainty. Dominance is evaluated using the appropriate hypothesis testing with specified confidence for a small sample, and the sample incrementally increased until dominance conditions can be determined. The method is demonstrated in the context of a tradeoff study for an automobile transmission.