In sequential testing an observer must choose when to observe additional data points and when to stop observation and make a decision. This stopping rule is traditionally based upon probability of error as well as certain cost parameters. The proposed stopping rule will instruct the observer to cease observation once the expected cost of the next observation increases. There is often a great deal of information about what the observer should see. This information will be used to develop a prior distribution for the parameters. The proposed stopping rule will be analyzed and compared to other stopping rules. Analysis of simulated data shows under which conditions the cost of the proposed stopping rule will approximate the minimum expected cost. / Department of Mathematical Sciences

Environmental stress screening is used to enhance reliability by decreasing the number of failures experienced during customer use. It is suggested that added benefit can be gained by applying multiple stresses rather than a single stress, as is done presently. A further modification is to apply the stress at the assembly level, accelerating different types of components at the same time. Different component E A e acceleration effects must then be considered. The problem these modifications present is how to choose the appropriate stress levels and the time duration of the stress screen. A cost model is developed that trades off the cost of a field failure with the cost of applying a multiple stress, multiple component stress screen. The objective is to minimize this cost function in order to find an economical stress regimen. The problem is solved using the software package GINO. The interesting result is that if a stress is used at all during the stress screen, the maximum amount of stress is the economic choice. Either the cost of stressing is low enough to justify the use of a stress, in which case the maximum amount of stress is used, or the cost is too high and the stress is not used at all. / Master of Science