C-PK INDEX ESTIMATION USING TRANSFORMATION

Process capability (PCIs) are used in industry to assess percentages o f nonconforming parts. An underlying assumption is that the output pro cess measurements are distributed as normal random variables. When nor mal distributions are assumed, but different distributions are present - such as skew, heavy-tailed, and short-tailed distributions - the pe rcentages of nonconforming parts are significantly different than the computed PCIs indicate. Data arising from nonnormal distributions can sometimes be transformed to conform to the normality assumptions and t he PCI's computed for the transformed data. In this paper, the effect of the transformation of the estimate of nonconforming parts is examin ed for three examples of nonnormal distributions - gamma, lognormal, a nd Weibull. The results of this experimental analysis suggest that dat a transformation can be useful for estimation an interval for C-pk val ues and the number of nonconforming parts.