Unit and Group-Runs Chart to Identify Increases in Fraction Nonconforming

Abstract

In this paper, we propose a control chart, called the “unit and group runs” (UGR) chart, which is useful to detect an increase in fraction nonconforming. The proposed chart starts with unit-level inspection and switches to the group-level inspection and back to the unit-level inspection according to a specified rule. The UGR chart gives a remarkable reduction in out-of-control average time to signal (ATS) as compared with the run-length CUSUM (Bourke (1991)), Bernoulli CUSUM (Reynolds and Stoumbos (1999)) and the synthetic control chart (Wu et al. (2001)). The proposed chart almost attains the lower bound for the out-of-control ATS and, hence, based on the ATS criterion, it is expected to outperform the other attribute-control charts. The steady-state performance of the proposed chart is also uniformly remarkable as compared with the other matched attribute-control charts. Therefore, the UGR chart for attributes enhances the effectiveness of statistical process control.

• Average Time to Signal
• Bernoulli CUSUM Chart
• Binomial CUSUM Chart
• CRL Chart
• np Chart
• Poisson CUSUM Chart
• Run-Length CUSUM Chart
• Steady State
• Synthetic Control Chart

Additional information

Notes on contributors

M. P. Gadre

Mr. M. P. Gadre is Lecturer in Statistics at Mudhoji College. His email address is [email protected].

R. N. Rattihalli

Dr. R. N. Rattihalli is Professor and Head of the Department of Statistics. His email address is [email protected].