Development of probability-limits-based control chart using copula functions and cox proportional hazards model

Document Type : Original Article

Authors

Department of Industrial Engineering, NT.C., Islamic Azad University, Tehran, Iran.

Abstract
Purpose: The aim of this study is to develop a novel framework for designing probability-limit-Based control chart to jointly monitor the time between events and event intensity while accounting for their dependence and the effects of observable covariates.
Methodology: In this study, First, the dependence between the time between events and event intensity is modeled using the Archimedean Clayton, Frank, and Gumbel copulas. Subsequently, the Cox proportional hazards model is employed to account for the effects of observable covariates on event occurrence times. Based on the marginal distributions of the variables and the dependence structure specified by the copula, a ratio-based monitoring statistic is defined and the corresponding upper control limit is determined. The performance of the proposed monitoring approaches is then evaluated and compared under various shift scenarios involving changes in the time between events, event intensity, and simultaneous shifts in both variables, across different levels of dependence and copula models, using the Average Run Length (ARL) as the performance criterion.
Findings: The results show that incorporating the effects of observable covariates through the Cox proportional hazards model, particularly under simultaneous-shift scenarios, enhances the sensitivity of the proposed monitoring approach, resulting in lower ARL values. Furthermore, comparison of the copula functions demonstrates that the appropriate specification of the dependence structure plays a critical role in control chart performance, with its importance becoming particularly evident when simultaneous changes occur in the time between events and event intensity.
Originality/Value: The main novelty of this study lies in developing an integrated framework for monitoring event data that simultaneously accounts for the dependence between the time between events and event intensity and the effects of observable covariates within the control chart structure. In this framework, copula functions are employed to model the dependence structure, while the Cox proportional hazards model is used to incorporate the effects of observable covariates. This integration provides a more flexible and realistic framework for monitoring processes in which event timing and intensity are interdependent and influenced by observable factors.

Keywords

Subjects

[1]     Calvin, T. (1983). Quality control techniques for" zero defects". IEEE Transactions on Components, Hybrids, and Manufacturing Technology, 6(3), 323–328. https://doi.org/10.1109/TCHMT.1983.1136174
[2]     Chan, L. Y., Xie, M., & Goh, T. N. (2000). Cumulative quantity control charts for monitoring production processes. International Journal of Production Research, 38(2), 397–408. https://doi.org/10.1080/002075400189482
[3]     Xie, M., Goh, T. N., & Ranjan, P. (2002). Some effective control chart procedures for reliability monitoring. Reliability Engineering & System Safety, 77(2), 143–150. https://doi.org/10.1016/S0951-8320(02)00041-8
[4]     Borror, C. M., Champ, C. W., & Rigdon, S. E. (1998). Poisson EWMA control charts. Journal of Quality Technology, 30(4), 352–361. https://doi.org/10.1080/00224065.1998.11979871
[5]     Chakraborti, S., Kumar, N., Rakitzis, A. C., & Sparks, R. S. (2014). Time between events monitoring with control charts. Wiley Statsref: Statistics Reference Online, 1–13. https://doi.org/10.1002/9781118445112.stat08409
[6]     Mirzaei Novin, M., Amiri, A., & Castagliola, P. (2026). A comprehensive review of time between events control charts: Models, applications, and future directions. Applications, and Future Directions. https://doi.org/10.1016/j.cie.2025.111789
[7]     Zhang, C. W., Xie, M., Liu, J. Y., & Goh, T. N. (2007). A control chart for the Gamma distribution as a model of time between events. International Journal of Production Research, 45(23), 5649–5666. https://doi.org/10.1080/00207540701325082
[8]     Wang, F.-K., Bizuneh, B., & Abebe, T. H. (2017). A comparison study of control charts for Weibull distributed time between events. Quality and Reliability Engineering International, 33(8), 2747–2759. https://doi.org/10.1002/qre.2238
[9]     Wu, Z., Jiao, J., & He, Z. (2009). A single control chart for monitoring the frequency and magnitude of an event. International Journal of Production Economics, 119(1), 24–33. https://doi.org/10.1016/j.ijpe.2009.01.004
[10]   Qu, L., Wu, Z., Khoo, M. B. C., & Castagliola, P. (2013). A CUSUM scheme for event monitoring. International Journal of Production Economics, 145(1), 268–280. https://doi.org/10.1016/j.ijpe.2013.04.048
[11]   Cheng, Y., Mukherjee, A., & Xie, M. (2017). Simultaneously monitoring frequency and magnitude of events based on bivariate gamma distribution. Journal of Statistical Computation and Simulation, 87(9), 1723–1741. https://doi.org/10.1080/00949655.2017.1284846
[12]   Rahali, D., Castagliola, P., Taleb, H., & Khoo, M. B. C. (2019). Evaluation of Shewhart time-between-events-and-amplitude control charts for several distributions. Quality Engineering, 31(2), 240–254. https://doi.org/10.1080/08982112.2018.1479036
[13]   Rahali, D., Castagliola, P., Taleb, H., & Khoo, M. B. C. (2021). Evaluation of Shewhart time-between-events-and-amplitude control charts for correlated data. Quality and Reliability Engineering International, 37(1), 219–241. https://doi.org/10.1002/qre.2731
[14]   Castagliola, P., Celano, G., Rahali, D., & Wu, S. (2021). Control charts for monitoring time-between-events-and-amplitude data. In Control Charts and Machine Learning for Anomaly Detection in Manufacturing (pp. 43–76). Springer. https://doi.org/10.1007/978-3-030-83819-5_3
[15]   Wu, S., Castagliola, P., & Celano, G. (2021). A distribution-free EWMA control chart for monitoring time-between-events-and-amplitude data. Journal of Applied Statistics, 48(3), 434–454. https://doi.org/10.1080/02664763.2020.1729347
[16]   He, Z., Gao, Y., Qu, L., & Wang, Z. (2022). A nonparametric CUSUM scheme for monitoring multivariate time-between-events-and-amplitude data with application to automobile painting. International Journal of Production Research, 60(18), 5432–5449. https://doi.org/10.1080/00207543.2021.1959664
[17]   Xue, L., An, L., Feng, S., Liu, Y., Wu, H., & Wang, Q. (2024). A nonparametric adaptive EWMA control chart for monitoring multivariate time-between-events-and-amplitude data. Computers & Industrial Engineering, 193, 110250. https://doi.org/10.1016/j.cie.2024.110250
[18]   Figueiredo, F. O., Castagliola, P., & Malela-Majika, J.-C. (2025). Rank-Based EWMA TBEA Control Chart. Quality and Reliability Engineering International, 41(4), 1279–1292. https://doi.org/10.1002/qre.3711
[19]   Scagliarini, M. (2026). Non-parametric time between events and amplitude methods for monitoring regional drought characteristics. Environmental and Ecological Statistics, 1–27. https://doi.org/10.1007/s10651-026-00760-3
[20]   Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological), 34(2), 187–202. https://doi.org/10.1111/j.2517-6161.1972.tb00899.x
[21]   Andersen, P. K., & Gill, R. D. (1982). Cox’s regression model for counting processes: a large sample study. The Annals of Statistics, 1100–1120. https://doi.org/10.1214/aos/1176345976
[22]   Prentice, R. L., Williams, B. J., & Peterson, A. V. (1981). On the regression analysis of multivariate failure time data. Biometrika, 68(2), 373–379.
[23]   Wei, L.-J., Lin, D. Y., & Weissfeld, L. (1989). Regression analysis of multivariate incomplete failure time data by modeling marginal distributions. Journal of the American Statistical Association, 84(408), 1065–1073. https://doi.org/10.1080/01621459.1989.10478873
[24]   Ahmad, H., Nadi, A. A., Amini, M., & Chakraborti, S. (2026). Dynamic Risk-adjusted monitoring of time between events: Applications of NHPP in pipeline accident surveillance. Quality and Reliability Engineering International, 42(1), 478–502. https://doi.org/10.1002/qre.70066
[25]   Chong, Z. L., Teoh, W. L., Khoo, M. B. C., Teh, S. Y., & Khaw, K. W. (2025). Dynamic VSI Max-EWMA control chart for joint monitoring of time-between-events and amplitude in high-quality manufacturing processes. Computers & Industrial Engineering, 207, 111204. https://doi.org/10.1016/j.cie.2025.111204
[26]   Alevizakos, V., & Koukouvinos, C. (2020). A progressive mean control chart for monitoring time between events. Quality and reliability engineering international, 36(1), 161–186. https://doi.org/10.1002/qre.2565
[27]   Chakraborty, N., Human, S. W., & Balakrishnan, N. (2017). A generally weighted moving average chart for time between events. Communications in Statistics-Simulation and Computation, 46(10), 7790–7817. https://doi.org/10.1080/03610918.2016.1252397
[28]   Sanusi, R. A., Teh, S. Y., & Khoo, M. B. C. (2020). Simultaneous monitoring of magnitude and time-between-events data with a Max-EWMA control chart. Computers & Industrial Engineering, 142, 106378. https://doi.org/10.1016/j.cie.2020.106378
[29]   Nelsen, R. B. (2006). An introduction to copulas. Springer. https://doi.org/10.1007/0-387-28678-0
[30]   Joe, H. (2014). Dependence modeling with copulas. CRC press. https://copula.stat.ubc.ca/