SYNOPTIC ABSTRACT
The two well-known unilateral specification process capability indices CPL and CPU are popularly used for measuring the process capability of larger-the-better type or smaller-the-better type products in the manufacturing industry. The practitioners can use them to determine whether their processes meet the capability requirement and select the better supplier. Under normal assumption, Chou (1994) developed an effective procedure using estimators of CPL and CPU for practitioners to determine whether two processes have equal capability or not. His works will be extended to the case of k processes. We take the tests of testing the equality of coefficients of variation from k populations and a new proposed test, the Modified-Bartlett's test, to determine whether k processes have equal capability or not. By Monte Carlo experiments, we have demonstrated that Modified-Bartlett's test has appropriate empirical size and has higher power than others. We also present a testing procedure that is convenient for practitioners to select the better supplier step by step.