Deviance and Pearson Residuals-Based Control Charts with Different Link Functions for Monitoring Logistic Regression Profiles: An Application to COVID-19 Data

Abstract

In statistical process control, the control charts are an effective tool to monitor the process. When the process is examined based on an exponential family distributed response variable along with a single explanatory variable, the generalized linear model (GLM) provides better estimates and GLM-based charts are preferred. This study is designed to propose GLM-based control charts using different link functions (i.e., logit, probit, c-log-log, and cauchit) with the binary response variable. The Pearson residuals (PR)- and deviance residuals (DR)-based control charts for logistic regression are proposed under different link functions. For evaluation purposes, a simulation study is designed to evaluate the performance of the proposed control charts. The results are compared based on the average run length (ARL). Moreover, the proposed charts are implemented on a real application for COVID-19 death monitoring. The Monte Carlo simulation study and real applications show that the performance of the model-based control charts with the c-log-log link function gives a better performance as compared to model-based control charts with other link functions.

A random forest-based analysis of cassava mosaic disease-related factors affecting the on-farm livelihoods of cassava farmers

“…The Random Forest model used in this study was evaluated, for each of the target variables, using ten (10) metrics -coefficient of determination (R 2 ) (Piepho, 2018;Jones, 2019;Hawinkel et al, 2024), the mean squared error (MSE) (Das et al, 2004;Kato & Hotta, 2021;Kim et al, 2021;Jin & Montúfar, 2023), the root mean squared error (RMSE) (Zollanvari & Dougherty, 2013;Busch et al, 2014;Huang et al, 2017;Belliardo & Giovannetti, 2020;Zhu, 2022;Reiter & Werner, 2024), the mean absolute error (MAE) (De Myttenaere et al, 2015aQi et al, 2020a, b;Baumgärtner et al, 2023;Wang et al, 2023;Xie, 2024), the mean absolute percentage error (MAPE) (De Myttenaere et al, 2015b), the maximum error (ME) (Lingasubramanian et al, 2011), the mean pinball loss (MPL) (Sluijterman et al, 2024), the mean gamma deviance (MGD) (Cheema et al, 2023), the mean Poisson deviance (MPD) (Oliveira et al, 2023) and the mean Tweedie deviance (MTD) (Wüthrich & Merz, 2023).…”

Global contribution of statistical control charts to epidemiology monitoring: A 23-year analysis with optimized EWMA real-life application on COVID-19

“…[19][20][21][22] Furthermore, in the context of COVID-19 death monitoring by using control charts following studies proposed different charts and identified death patterns. [23][24][25][26][27] Medical information determines control chart classification. There may be continuous, count, or attribute-based data.…”

“…[19–22] Furthermore, in the context of COVID-19 death monitoring by using control charts following studies proposed different charts and identified death patterns. [23–27]…”

Preface to the Special Issue on “Computational and Mathematical Methods in Information Science and Engineering”

“…The paper authored by Cheema et al [2] studies GLM-based control charts using different link functions (i.e., logit, probit, c-log-log, and cauchit) with the binary response variable. The Pearson residuals (PR)-and deviance residuals (DR)-based control charts for logistic regression are proposed under different link functions.…”