Bootstrap Sequential Fixed-Width Confidence Interval Estimation of Process Capability Index CPM

Construction of confidence interval for process capability index C-PM is often based on a normal approximation with fixed sample size. We describe a different approach to constructing fixed-width confidence interval for process capability index C-PM with a preassigned accuracy using the smallest possible sample size. This optimal sample size is obtained using both two-stage and modified two-stage sequential procedures. A methodology is developed for determining whether it is advantageous to use the bootstrap technique to optimize sample size. The procedure developed is also validated using an extensive simulation study.