The indices Cp and Cpk are extensively used to assess process capability. However, they only take into
account the process mean and standard deviation, but not the proximity of the process mean to the target
value, T, of the process characteristic. Cp,m does take into account the proximity of the process mean to
the target value. We propose a method for selecting or judging the better of two suppliers or processes
based on a confidence interval for the ratio Cpml/Cpm2. Four methods of obtaining approximate confidence
intervals are presented and compared, one based on the statistical theory given in Boyles (1991) and three
based on the bootstrap, (referred to as SB (standard bootstrap), PB (percentile bootstrap), and BCPB
(biased-corrected percentile bootstrap)). The performance was compared using simulation, which showed
that, in two independent and normal process environments, Boyles's (1991) confidence interval and the SB
confidence interval are more reliable than the PB and BCPB methods. A sample size of greater than 50 is
recommended for selecting the most capable of two suppliers or processes.
