The 𝑛𝑝-Chart with 3-𝜎 Limits and the ARL-Unbiased 𝑛𝑝-Chart Revisited

Morais Manuel Cabral (), Wittenberg Philipp () and Cruz Camila Jeppesen ()
Additional contact information
Morais Manuel Cabral: Department of Mathematics & CEMAT (Center for Computational and Stochastic Mathematics), Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisboa, Portugal
Wittenberg Philipp: Department of Mathematics and Statistics, Helmut Schmidt University, Holstenhofweg 85, 22043 Hamburg, Germany
Cruz Camila Jeppesen: Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisboa, Portugal

Stochastics and Quality Control, 2022, vol. 37, issue 2, 107-116

Abstract: In the statistical process control literature, counts of nonconforming items are frequently assumed to be independent and have a binomial distribution with parameters ( n , p ) (n,p) , where 𝑛 and 𝑝 represent the fixed sample size and the fraction nonconforming. In this paper, the traditional n ⁢ p np -chart with 3-𝜎 control limits is reexamined. We show that, even if its lower control limit is positive and we are dealing with a small target value p 0 p_{0} of the fraction nonconforming ( p ) (p) , this chart average run length (ARL) function achieves a maximum to the left of p 0 p_{0} . Moreover, the in-control ARL of this popular chart is also shown to vary considerably with the fixed sample size 𝑛. We also look closely at the ARL function of the ARL-unbiased n ⁢ p np -chart proposed by Morais [An ARL-unbiased n ⁢ p np -chart, Econ. Qual. Control 31 (2016), 1, 11–21], which attains a pre-specified maximum value in the in-control situation. This chart triggers a signal at sample 𝑡 with probability one if the observed number of nonconforming items, x t x_{t} , is beyond the lower and upper control limits (𝐿 and 𝑈), probability γ L \gamma_{L} (resp. γ U \gamma_{U} ) if x t x_{t} coincides with 𝐿 (resp. 𝑈). A graphical display for the ARL-unbiased n ⁢ p np -chart is proposed, taking advantage of the qcc package for the statistical software R. Furthermore, as far as we have investigated, its control limits can be obtained using three different search algorithms; their computation times are thoroughly compared.

Keywords: Average Run Length; Randomization Probabilities; Statistical Process Control (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1515/eqc-2022-0032 (text/html)
For access to full text, subscription to the journal or payment for the individual article is required.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bpj:ecqcon:v:37:y:2022:i:2:p:107-116:n:2

Ordering information: This journal article can be ordered from
https://www.degruyter.com/journal/key/eqc/html

DOI: 10.1515/eqc-2022-0032

Access Statistics for this article

Stochastics and Quality Control is currently edited by George P. Yanev

More articles in Stochastics and Quality Control from De Gruyter
Bibliographic data for series maintained by Peter Golla ().