An hypothesis test technique for determining a difference in sampled parts defective utilizing Fisher´s exact test IC production

The result of sample testing during the production of integrated circuits is often a very small number of parts defective out of a sample which is itself very small compared to its population. The ability to determine a statistically significant difference when comparing the results of two such samples is critical in correctly evaluating the outcome of experiments. Fisher´s exact test can be used in this situation because it is a method for testing the difference between two proportions of parts defective when the proportions are relatively small in comparison to the sample size. The results of the test are very accurate when the populations are at least ten times the sample size. The result of the test is independent of the order of the samples. However, because the test is one-sided, care must be taken to state the alternative hypothesis based upon the order of the magnitudes of the sample fractions defective