Abstract:
This research aims to propose the Markov Chain Approach (MCA) to evaluate the Average Run Length (ARL) of Exponentially Weighted Moving Average (EWMA) and Cumulative Sum (CUSUM) control charts for Zero-inflated Negative Binomial type II (ZINB) process by comparing the estimates of ARL obtained from the MCA with the results obtained from the Monte Carlo Simulation (MC). Furthermore, we propose an approximation of ARL by deriving the explicit formulas (EF) for Moving Average (MA) and Double Moving Average (DMA) control charts for ZINB process. The performance among EWMA, CUSUM, MA and DMA control charts for ZINB process are compared in terms of ARL1 when the process is out-of-control. The numerical results obtained from the MCA are closed to those from the MC but the MCA is much saving computational times used when compared with the MC. The ARL by EF are simple and easy to implement. The results show that DMA control chart performs better for small shifts, nevertheless MA control chart performs better when shifts are large.