Mm Manene

Step-wise group screening designs with errors in observations

The performance of step-wise group screening In terms of the expected number of runs and the expected number of incorrect decisions, Is considered. A method for obtaining optimal step-wise designs Is presented, for the cases in which the direction of each defective factor is assumed to be known a-priori and the observations are subject to error.

Step-wise screening of defective factors

It is generally assumed that the defective factors of a population have the same a-priori probability of being defective. However,with some knowledge of the population, we can relax on this assumption and assume the population may consist of factors with unequal a-priori probabilities of being defective. Step-wise screening is developed to detect these factors with minimum expected number of runs assuming that there are no errors in the observationso Comparison is done with an equivalent two-stage group screening experiment.