A new omnibus SPRT chart for monitoring process mean and variability based on the average number of observations to signal

Journal: Journal of Statistical Computation and Simulations, WoS(SCIE), Q2
Author: Trần Kim Phúc - Trường Đại học Đông Á

Abstract:

The recent development of the omnibus sequential probability ratiotest (OSPRT) chart marks a significant contribution to the advance-ment of joint monitoring schemes. As the OSPRT chart is a variable-sample-size control chart, practitioners often wish to understandits inspection efficiency, i.e. the number of observations it samplesbefore producing a signal. In this article, we propose two enhancedoptimization designs for the OSPRT chart based on the average num-ber of observations of signal (ANOS) and expected value of theANOS (EANOS) metrics under deterministic and unknown shift sizes,respectively. The ANOS metric is central to our design as it perfectlycombines both the average run length (ARL) and the average samplenumber. A comparative analysis reveals that the OSPRT chart out-performs four benchmarking control charts in terms of the ANOSand EANOS metrics. Finally, an implementation of the OSPRT chartis presented with a ball shear test dataset

DOI: A new omnibus SPRT chart for monitoring process mean and variability based on the average number of observations to signal