Published

2022-01-01

Evaluation of the Mean Control Chart Under a Bayesian Approach

Evaluación de la carta de control para la media de un proceso bajo un enfoque bayesiano

DOI:

https://doi.org/10.15446/rce.v45n1.93588

Keywords:

Control charts, Bayesian Approach, ARL, Conjugate prior, Informative prior (en)
Gráficas de control, Enfoque Bayesiano, ARL, Distribución a priori conjugada, Distribución a priori informativa (es)

Downloads

Authors

  • Isabel Cristina Ramirez Guevara Universidad Nacional de Colombia
  • Nelfi González-Álvarez Universidad Nacional de Colombia

A previous study on the evaluation of control charts for the mean with a Bayesian approach, based on predictive limits, was performed in such a way that neither prior nor sample information was taken into account. This work was developed to make a more complete study to evaluate the influence of the combination of the prior distribution with the sample information. It is assumed that the quality characteristic to be controlled can be modeled by a Normal distribution and two cases are considered: known and unknown variance. A Bayesian conjugate model is established, therefore the prior distribution for the mean is Normal and, in the case where the variance is unknown, the prior distribution for the variance is defined as the Inverse-Gamma(ν, ν). The posterior predictive distribution, which is also Normal, is used to establish the control limits of the chart. Signal propability is used to measure the performance of the control chart in phase II, with the predictive limits calculated under different specifications of the prior distributions, and two different sizes of the calibration sample and the future sample. The simulation study evaluates three aspects: the effects of sample sizes, the distance of the prior mean to the mean of the calibration sample, and an indicator of how informative is the prior distribution of the population mean. In addition, in the case of unknown variance, we study what is the effect of changing values in the parameter ν. We found that the false alarm rate could be quite large if the prior distribution is very informative which in turn leads to an ARL (average run length) biased chart, that is, the maximum of the ARL is not given when the process is under control. Besides, we found
great influence of the prior distribution on the control chart power when the size of the calibration and future samples are small, particulary when the prior is very informative. Finally, regarding the effect of the parameter ν, we found that the smaller the value, which means having a less informative prior distribution, the lower the power of the control chart. 

Un estudio previo sobre la evaluación de las gráficas de control para la media con un enfoque Bayesiano, basadas en límites predictivos, fue realizado de tal manera que no se tuvo en cuenta ni la información a priori ni la información muestral. En este trabajo hemos desarrollado un estudio más completo para evaluar la influencia de la combinación de la distribución a priori con la información muestral. Se asume que la característica de calidad a controlar puede modelarse mediante una distribución Normal y se consideran dos casos: varianza conocida y desconocida. Para la aproximación Bayesiana se establece un modelo conjugado, por lo tanto la distribución a priori para la media es Normal y, en el caso donde la varianza es desconocida, se define como distribución a priori para la varianza la Gamma-Inversa(ν, ν). La distribución predictiva posterior, que también es Normal, es utilizada para establecer los límites de control de la gráfica. Se utiliza la probabilidad de señal para medir el desempeño de la gráfica en la denominada phase II de control, con los límites predictivos calculados bajo diferentes especificaciones de las distribuciones a priori, del tamaño de la muestra de calibración y del tamaño de la muestra futura. El estudio de simulación evalúa tres aspectos: efectos del tamaño de muestra, de la distancia de la media a priori con relación a la media de la muestra de calibración, y un indicador de cuán informativa es la distribución a priori de la media poblacional. Adicionalmente, cuando la varianza es desconocida, se estudia el efecto de los valores del parámetro ν. Se encuentra que la tasa de falsas alarmas puede ser exageradamente grande si se especifica una a priori muy informativa, lo que a su vez puede conducir a una gráfica de control con una ARL (average run length) sesgada, es decir, que el máximo de la ARL no se dará cuando el proceso está en control. Además, cuando el tamaño de las muestras de calibración y de la muestra futura son pequeñas, hay gran influencia de la especificación de la a priori sobre la potencia de la gráfica de control, en especial cuando la a priori es muy informativa. Finalmente, en cuanto al efecto del parámetro ν, se encuentra que entre más pequeño es su valor, lo cual indica que la distribución a priori para la varianza es menos informativa,
menor es la potencia de la gráfica de control, en especial si los tamaños de
muestra son pequeños.

References

Ali, S. & Riaz, M. (2020), ‘On designing a new bayesian dispersion chart for process monitoring’, Arabian Journal for Science and Engineering 45, 2093–2111. DOI: https://doi.org/10.1007/s13369-019-04036-w

Bhat, S. V. & Gokhale, K. D. (2014), ‘Posterior Control Chart for Process Average under Conjugate Prior Distribution’, Economic Quality Control 29(1), 19–27. DOI: https://doi.org/10.1515/eqc-2014-0003

Chen, Y. (2016), ‘A New Type of Bayesian Nonparametric Control Charts for Individual Measurements’, Journal of Statistical Theory and Practice 10(1), 226–238. DOI: https://doi.org/10.1080/15598608.2015.1117405

Colosimo, B. M. & del Castillo, E. (2007), Bayesian process monitoring, control and optimization, Chapman & Hall/CRC, Boca Raton, FL. DOI: https://doi.org/10.1201/9781420010701

Gelman, A. (2006), ‘Prior distributions for variance parameters in hierarchical models: Comment on article by browne and draper’, Bayesian Analysis 1(3), 515–534. DOI: https://doi.org/10.1214/06-BA117A

Jensen, W. A., Jones-Farmer, L. A., Champ, C. W. & Woodall, W. H. (2006), ‘Effects of parameter estimation on control chart properties: A literature review’, Journal of Quality Technology 38(4), 349–364. DOI: https://doi.org/10.1080/00224065.2006.11918623

Menzefricke, U. (2002), ‘On the evaluation of control chart limits based on predictive distributions’, Communications in Statistics - Theory and Methods 31(8), 1423–1440. DOI: https://doi.org/10.1081/STA-120006077

Monfared, M. E. D. & Lak, F. (2013), ‘Bayesian estimation of the change point using ¯X control chart’, Communications in Statistics - Theory and Methods 42(8), 1572–1582. DOI: https://doi.org/10.1080/03610926.2011.594536

Nenes, G. (2013), ‘Optimisation of fully adaptive Bayesian charts for infinitehorizon processes’, International Journal of Systems Science 44(2), 289–305. DOI: https://doi.org/10.1080/00207721.2011.600475

Nikolaidis, Y. & Tagaras, G. (2017), ‘New indices for the evaluation of the statistical properties of Bayesian ¯x control charts for short runs’, European Journal of Operational Research 259(1), 280–292. DOI: https://doi.org/10.1016/j.ejor.2016.09.039

Psarakis, S., Vyniou, A. K. & Castagliola, P. (2014), ‘Some recent developments on the effects of parameter estimation on control charts’, Quality and Reliability Engineering International 30(8), 1113–1129. DOI: https://doi.org/10.1002/qre.1556

Saghir, A. (2015), ‘Phase-I Design Scheme for ¯x chart Based on Posterior Distribution’, Communications in Statistics - Theory and Methods 44(3), 644–655. DOI: https://doi.org/10.1080/03610926.2012.752846

Shewhart, W. A. (1931), Economic control of quality of manufactured product, Van Nostrand., (Reprinted by The American Society for Quality Control, 1980), New York.

Tagaras, G. & Nikolaidis, Y. (2002), ‘Comparing the effectiveness of various bayesian ¯X control charts’, Operations Research 50(5), 878–888. DOI: https://doi.org/10.1287/opre.50.5.878.361

Tsiamyrtzis, P. & Hawkins, D. M. (2005), ‘A bayesian scheme to detect changes in the mean of a short-run process’, Technometrics 47(4), 446–456. DOI: https://doi.org/10.1198/004017005000000346

Woodall, W. H. (2000), ‘Controversies and contradictions in statistical process control’, Journal of Quality Technology 32(4), 341–350. DOI: https://doi.org/10.1080/00224065.2000.11980013

Woodall, W. H. & Montgomery, D. C. (1999), ‘Research issues and ideas in statistical process control’, Journal of Quality Technology 31(4), 376–386. DOI: https://doi.org/10.1080/00224065.1999.11979944

Woodall, W. H. & Montgomery, D. C. (2014), ‘Some current directions in the theory and application of statistical process monitoring’, Journal of Quality Technology 46(1), 78–94. DOI: https://doi.org/10.1080/00224065.2014.11917955

Xiaosong, W., Rui, M., Xinyi, Z., Zhibin, J. & Xuening, C. (2015), ‘A conjugate Bayesian approach to control chart for multi-batch and low volume production’, International Journal of Production Research 53(7), 2179–2185. DOI: https://doi.org/10.1080/00207543.2014.975857

How to Cite

APA

Ramirez Guevara, I. C. and González-Álvarez, N. (2022). Evaluation of the Mean Control Chart Under a Bayesian Approach. Revista Colombiana de Estadística, 45(1), 85–105. https://doi.org/10.15446/rce.v45n1.93588

ACM

[1]
Ramirez Guevara, I.C. and González-Álvarez, N. 2022. Evaluation of the Mean Control Chart Under a Bayesian Approach. Revista Colombiana de Estadística. 45, 1 (Jan. 2022), 85–105. DOI:https://doi.org/10.15446/rce.v45n1.93588.

ACS

(1)
Ramirez Guevara, I. C.; González-Álvarez, N. Evaluation of the Mean Control Chart Under a Bayesian Approach. Rev. colomb. estad. 2022, 45, 85-105.

ABNT

RAMIREZ GUEVARA, I. C.; GONZÁLEZ-ÁLVAREZ, N. Evaluation of the Mean Control Chart Under a Bayesian Approach. Revista Colombiana de Estadística, [S. l.], v. 45, n. 1, p. 85–105, 2022. DOI: 10.15446/rce.v45n1.93588. Disponível em: https://revistas.unal.edu.co/index.php/estad/article/view/93588. Acesso em: 24 apr. 2024.

Chicago

Ramirez Guevara, Isabel Cristina, and Nelfi González-Álvarez. 2022. “Evaluation of the Mean Control Chart Under a Bayesian Approach”. Revista Colombiana De Estadística 45 (1):85-105. https://doi.org/10.15446/rce.v45n1.93588.

Harvard

Ramirez Guevara, I. C. and González-Álvarez, N. (2022) “Evaluation of the Mean Control Chart Under a Bayesian Approach”, Revista Colombiana de Estadística, 45(1), pp. 85–105. doi: 10.15446/rce.v45n1.93588.

IEEE

[1]
I. C. Ramirez Guevara and N. González-Álvarez, “Evaluation of the Mean Control Chart Under a Bayesian Approach”, Rev. colomb. estad., vol. 45, no. 1, pp. 85–105, Jan. 2022.

MLA

Ramirez Guevara, I. C., and N. González-Álvarez. “Evaluation of the Mean Control Chart Under a Bayesian Approach”. Revista Colombiana de Estadística, vol. 45, no. 1, Jan. 2022, pp. 85-105, doi:10.15446/rce.v45n1.93588.

Turabian

Ramirez Guevara, Isabel Cristina, and Nelfi González-Álvarez. “Evaluation of the Mean Control Chart Under a Bayesian Approach”. Revista Colombiana de Estadística 45, no. 1 (January 19, 2022): 85–105. Accessed April 24, 2024. https://revistas.unal.edu.co/index.php/estad/article/view/93588.

Vancouver

1.
Ramirez Guevara IC, González-Álvarez N. Evaluation of the Mean Control Chart Under a Bayesian Approach. Rev. colomb. estad. [Internet]. 2022 Jan. 19 [cited 2024 Apr. 24];45(1):85-105. Available from: https://revistas.unal.edu.co/index.php/estad/article/view/93588

Download Citation

CrossRef Cited-by

CrossRef citations0

Dimensions

PlumX

Article abstract page views

242

Downloads

Download data is not yet available.