A Comparative Study of Control Charts for Zero-Inflated Binomial Processes

摘要

Zero-inflated probability models are recommended when there is an excessive number of zeros in count data. In the context of statistical process control, such cases arise in high-yield processes where the fraction of non-conforming units produced is very low. Other applications can be also found in the monitoring of health-related process, where it is of interest the monitoring of rare health-events like the number of congenital malformations or the rate of wound infections. In this work, we present one-sided and two-sided control charts that are suitable for the monitoring of changes in the parameters of a zero-inflated binomial process. We consider Shewhart-, EWMA- and CUSUM-type control charts, and we present aspects of their statistical design. Numerical comparisons between the different schemes are given as well.