Abstract
The generalization , a modification of the process capability index Cpm, not only takes the proximity of the target value into consideration but also takes into account the asymmetry of the specification limits. In this paper, based on the theory of testing hypothesis we develop a step-by-step procedure using estimator of
for the practitioners in making decisions when the process is normally distributed. An efficient MAPLE computer program is developed to calculate the corresponding p-value. For non-normal sample data, an example is presented that an approach based on Johnson transformation is to transform the nonnormal data to normality. The proposed decision making rule can be used to test whether the process is capable or not.
Keywords and phrases: