A partitioned weighted moving average control chart

Raja Fawad Zafar, Michael B.C. Khoo, Huay Woon You, Sajal Saha and Wai Chung Yeong

Journal of Applied Statistics, 2025, vol. 52, issue 3, 744-777

Abstract: A partitioned weighted moving average (PWMA) chart is developed by partitioning the samples (or observations) into two groups, calculating the groups’ weighted average and adding them. This partitioning gives more control over weight distribution in the most recent j (= 2, 3, …) samples. The PWMA, exponentially weighted moving average (EWMA) and homogenously weighted moving average (HWMA) charts are compared. For zero state, the PWMA chart outperforms the EWMA and HWMA charts for most (n, λ, δ) values and the outperformance of the former over the two latter charts increases with the time period (j), employed in the partitioning. Here, λ is the charts’ smoothing constant and δ is the shift size (multiples of standard deviation). For steady state, the PWMA chart (regardless of j) generally outperforms the EWMA chart in detecting a small shift (δ = 0.25) when the smoothing constant λ ≥ 0.2 for the sample size n = 1; while a larger λ is needed for n = 5. Moreover, for steady state, the PWMA chart outperforms the HWMA chart in detecting small and moderate shifts (0.25 ≤ δ ≤ 1), regardless of (λ, n, j). The PWMA chart demonstrates robustness to non-normality and estimated process parameters.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/02664763.2024.2392122 (text/html)
Access to full text is restricted to subscribers.

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:taf:japsta:v:52:y:2025:i:3:p:744-777

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/02664763.2024.2392122

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().