Bootstrap and Control Charts : Review and Future Directions

摘要

Usually, the performance of a manufacturing process will be monitored and controlled under conventional Shewhart control charts, fundamental tools of quality control used for detecting the presence of assignable causes (process shifts), and improving the process by the reduction of variability. These charts do not work well with non-normal data, leading us to consider alternatives. Bootstrap methods, a family of the resampling techniques, are considered in the application of statistical process control because they can deal with unknown distributions and are easy to calculate using a personal computer. Recent research about bootstrap and control charts will be reviewed in this paper. This leads to some suggestions for future study.