Javed Hina, Ismail Muhammad, Saeed Nadia
College of Statistical Sciences, University of the Punjab, Lahore Pakistan.
COMSATS University Islamabad Lahore, Campus Lahore Pakistan.
Heliyon. 2024 Jul 9;10(14):e34424. doi: 10.1016/j.heliyon.2024.e34424. eCollection 2024 Jul 30.
In this article, we develop a new control chart based on the Exponentially Weighted Moving Average (EWMA) statistic, termed the New Extended Exponentially Weighted Moving Average (NEEWMA) statistic, designed to recognize slight changes in the process mean. We derive expressions for the mean and variance of the NEEWMA statistic, ensuring an unbiased estimation of the mean, with simulation results showing lower variance compared to traditional EWMA charts. Evaluating its performance using Average Run Length (ARL), our analysis reveals that the NEEWMA control chart outperforms EWMA and Extended EWMA (EEWMA) charts in swiftly recognizing shifts in the process mean. Illustrating its operational methodology through Monte Carlo simulations, an illustrative example using practical data is also provided to showcase its effectiveness.
在本文中,我们基于指数加权移动平均(EWMA)统计量开发了一种新的控制图,称为新扩展指数加权移动平均(NEEWMA)统计量,旨在识别过程均值的微小变化。我们推导了NEEWMA统计量的均值和方差表达式,确保均值的无偏估计,模拟结果表明其方差低于传统的EWMA控制图。使用平均运行长度(ARL)评估其性能,我们的分析表明,NEEWMA控制图在快速识别过程均值的变化方面优于EWMA和扩展EWMA(EEWMA)控制图。通过蒙特卡罗模拟说明了其操作方法,还提供了一个使用实际数据的示例来说明其有效性。