學術產出-Theses
Article View/Open
Publication Export
-
題名 中位數和四分位距管制圖設計之研究
Study on Design of Median and IQR Control Charts for Monitoring Location and Dispersion作者 姜亭安 貢獻者 楊素芬
姜亭安關鍵詞 平均連串長度
不受分配限制
統計製程管制
雙次抽樣
Average run length
Distribution-free
Statistical process control
Double sampling日期 2016 上傳時間 20-Jul-2016 16:53:05 (UTC+8) 摘要 不論在製造流程或是其他產業上，管制圖是一個能夠監督流程失控的非常有效工具。不受分配限制的管制圖的發展對於非常態或分配未知的品質變數是非常重要的。根據無母數方法所建立的不受分配限制的管制圖對使用者來說是不容易的，因為他們並不是統計學家。本文提出了一種簡單的指數加權移動平均(EWMA)中位數和四分位距管制圖，採用單次抽樣方法和雙次抽樣方法以分別監控製程的位置與離散程度。此外，本文亦提出了一種核密度估計方法的管制區以同時監控製程的位置與離散程度。這裡以平均連串長度(ARL)來衡量所提出的管制圖的偵測效果。我們比較所提出的管制圖以及現有的一些不受分配限制的管制圖的偵測效果。以服務時間的示例來說明所提出的指數加權移動平均中位數管制圖、指數加權移動平均四分位距管制圖和核密度估計方法的管制區的應用。與其他現有的不受分配限制的管制圖相比，所提出的管制圖在製程的位置與離散有小幅度的偏移時有較好的偵測效果。因此，我們建議可以使用所提出的管制圖。
Control charts are effective tools for monitoring the process parameters in manufacturing processes and other industries. The development of distribution-free charts is important for non-normal or unknown distributed quality variable in statistical process control. The distribution-free control charts based on nonparametric statistics are not easy for practitioners to apply because they are not statisticians and do not know the scheme. This paper proposes a simple EWMA median chart and IQR char with single sampling scheme and double sampling scheme to monitor the location and dispersion, respectively. Furthermore, a kernel control region is proposed for monitoring the location and dispersion simultaneously. The average run lengths (ARL) is used to measure the detection performance of the proposed control chart(s). We compare the location and dispersion detection performance of the proposed charts and those of some existing distribution-free charts. An example of service times is used to illustrate the application of the proposed EWMA median and EWMA IQR charts and kernel control region. The proposed charts show superior detection performance compared to the existing distribution-free location and dispersion charts when the shifts in process location and/or dispersion are small. The SS EWMA-Md and DS EWMA-D charts and SS kernel control region are thus recommended.參考文獻 Bakir, S., & Reynolds, M. (1979). A Nonparametric Procedure for Process Control Based on Within-Group Ranking. Technometrics, 21, 175-183. [2] Chacón, J. E., & Duong, T. (2010). Multivariate plug-in bandwidth selection with unconstrained pilot bandwidth matrices. Test, 19(2), 375-398.[3] Chowdhury, S., Mukherjee, A., & Chakraborti, S. (2014). A New Distribution‐free Control Chart for Joint Monitoring of Unknown Location and Scale Parameters of Continuous Distributions. Quality and Reliability Engineering International, 30(2), 191-204. [4] Das, N. (2008). Non-parametric control chart for controlling variability based on rank test. Economic Quality Control, 23(2), 227-242. [5] Daudin, J. J. (1992). Double sampling X̄ charts. Journal of Quality Technology, 24(2), 78-87. [6] Downton, F. (1966). Linear estimates with polynomial coefficients. Biometrika, 53(1/2), 129-141. [7] Ghute, V. (2014). Nonparametric control chart for variability using runs rules. The Experiment, 24(4), 1683-1691. [8] Hawkins, D.M., and Olwell, D.H. (1998), Cumulative Sum Charts and Charting for Quality Improvement, New York: Springer-Verlag.[9] Hawkins, D.M., Qiu, P., and Chang Wook Kang (2003), The changepoint model for statistical process control. Journal of Quality Technology, 35, 355–366.[10] He, D., & Grigoryan, A. (2002). Construction of double sampling s‐control charts for agile manufacturing. Quality and Reliability Engineering International, 18(4), 343-355.[11] He, D., & Grigoryan, A. (2003). An improved double sampling s chart. International Journal of Production Research, 41(12), 2663-2679. [12] Hu, F.-S. (2015). Design of a Control Region for Monitoring Joint Location and Dispersion. [13] 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.[14] Jones, M. A., & Steiner, S. H. (2012). Assessing the effect of estimation error on risk-adjusted CUSUM chart performance. International Journal for Quality in Health Care, 24(2), 176-181.[15] Khoo, M. B. (2005). A control chart based on sample median for the detection of a permanent shift in the process mean. Quality engineering, 17(2), 243-257. [16] Lepage, Y. (1971). A combination of Wilcoxon`s and Ansari-Bradley`s statistics. Biometrika, 58(1), 213-217. [17] Liu, L., Tsung, F., & Zhang, J. (2014). Adaptive nonparametric CUSUM scheme for detecting unknown shifts in location. International Journal of Production Research, 52(6), 1592-1606. [18] Liu, R. Y., & Tang, J. (1996). Control charts for dependent and independent measurements based on bootstrap methods. Journal of the American Statistical Association, 91(436), 1694-1700. [19] Lucas, J. M., & Saccucci, M. S. (1990). Exponentially weighted moving average control schemes: properties and enhancements. Technometrics, 32(1), 1-12. [20] McCracken, A., & Chakraborti, S. (2013). Control charts for joint monitoring of mean and variance: an overview. Quality Technology & Quantitative Management, 10(1), 17-36.[21] Montgomery, D. C. (2009). Statistical quality control (Vol. 7): Wiley New York.[22] Mood AM. (1954). On the asymptotic efficiency of certain nonparametric two-sample tests. Annals of Mathematical Statistics 1954; 25: 514-522.[23] Mukherjee, A., & Chakraborti, S. (2012). A Distribution‐free Control Chart for the Joint Monitoring of Location and Scale. Quality and Reliability Engineering International, 28(3), 335-352. [24] Nelson, L. S. (1963). Tables for a precedence life test. Technometrics, 5(4), 491-499..[25] Nelson, L. S. (1993) Tests on early failures: the precedence life test. Journal of quality technology, 25(2), 140-143.[26] Page, E. (1954). Continuous inspection schemes. Biometrika, 41(1/2), 100-115.[27] Parzen, E. (1962). On estimation of a probability density function and mode. Annals of Mathematical Statistics 33: 1065–1076.[28] Rosenblatt, M. (1956). Remarks on some nonparametric estimates of a density function. Annals of Mathematical Statistics 27: 832–837[29] Shewhart, W. A. (1931). Economic control of quality of manufactured product: ASQ Quality Press.[30] Siegel, S., & Tukey, J. W. (1960). A nonparametric sum of ranks procedure for relative spread in unpaired samples. Journal of the American Statistical Association, 55(291), 429-445.[31] Stromberg, A., Griffith, W., & Smith, M. (2003). Control Charts for the Median and Interquartile Range. In R. Dutter, Filzmoser, P., Gather, U., Rousseeuw, P. (Ed.), International Conference on Robust Statistics 2001-Developments in Robust Statistics (pp. 368-376). Heidelberg GmbH: Springer-Verlag Berlin.[32] Sukhatme, B. V. (1957). On certain two-sample nonparametric tests for variances. The Annals of Mathematical Statistics, 28(1), 188-194.[33] Wu, C. F. (1990). On the asymptotic properties of the jackknife histogram. The Annals of Statistics, 1438-1452. [34] Yang, L., Pai, S., & Wang, Y. R. (2010). A novel CUSUM median control chart. Paper presented at the Proceedings of International Multiconference of Engineers and Computer Scientists.[35] Yang, S. F. (2013). Using a new VSI EWMA average loss control chart to monitor changes in the difference between the process mean and target and/or the process variability. Applied Mathematical Modelling, 37(16), 7973-7982. [36] Yang, S. F., & Arnold, B. C. (2014). A Simple Approach for Monitoring Business Service Time Variation. The Scientific World Journal, 2014, 238719. doi:10.1155/2014/238719[37] Yang, S. F., & Cheng, S. W. (2011). A new non‐parametric CUSUM mean chart. Quality and Reliability Engineering International, 27(7), 867-875. [38] Yang, S. F., Cheng, T. C., Hung, Y. C., & W Cheng, S. (2012). A new chart for monitoring service process mean. Quality and Reliability Engineering International, 28(4), 377-386. [39] Zhang, G. (2014). Improved R and s control charts for monitoring the process variance. Journal of Applied Statistics, 41(6), 1260-1273. doi:10.1080/02664763.2013.864264[40] Zou, C., & Tsung, F. (2010). Likelihood ratio-based distribution-free EWMA control charts. Journal of Quality Technology, 42(2), 174. 描述 碩士
國立政治大學
統計學系
103354005資料來源 http://thesis.lib.nccu.edu.tw/record/#G1033540051 資料類型 thesis dc.contributor.advisor 楊素芬 zh_TW dc.contributor.author (Authors) 姜亭安 zh_TW dc.creator (作者) 姜亭安 zh_TW dc.date (日期) 2016 en_US dc.date.accessioned 20-Jul-2016 16:53:05 (UTC+8) - dc.date.available 20-Jul-2016 16:53:05 (UTC+8) - dc.date.issued (上傳時間) 20-Jul-2016 16:53:05 (UTC+8) - dc.identifier (Other Identifiers) G1033540051 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/99315 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 統計學系 zh_TW dc.description (描述) 103354005 zh_TW dc.description.abstract (摘要) 不論在製造流程或是其他產業上，管制圖是一個能夠監督流程失控的非常有效工具。不受分配限制的管制圖的發展對於非常態或分配未知的品質變數是非常重要的。根據無母數方法所建立的不受分配限制的管制圖對使用者來說是不容易的，因為他們並不是統計學家。本文提出了一種簡單的指數加權移動平均(EWMA)中位數和四分位距管制圖，採用單次抽樣方法和雙次抽樣方法以分別監控製程的位置與離散程度。此外，本文亦提出了一種核密度估計方法的管制區以同時監控製程的位置與離散程度。這裡以平均連串長度(ARL)來衡量所提出的管制圖的偵測效果。我們比較所提出的管制圖以及現有的一些不受分配限制的管制圖的偵測效果。以服務時間的示例來說明所提出的指數加權移動平均中位數管制圖、指數加權移動平均四分位距管制圖和核密度估計方法的管制區的應用。與其他現有的不受分配限制的管制圖相比，所提出的管制圖在製程的位置與離散有小幅度的偏移時有較好的偵測效果。因此，我們建議可以使用所提出的管制圖。 zh_TW dc.description.abstract (摘要) Control charts are effective tools for monitoring the process parameters in manufacturing processes and other industries. The development of distribution-free charts is important for non-normal or unknown distributed quality variable in statistical process control. The distribution-free control charts based on nonparametric statistics are not easy for practitioners to apply because they are not statisticians and do not know the scheme. This paper proposes a simple EWMA median chart and IQR char with single sampling scheme and double sampling scheme to monitor the location and dispersion, respectively. Furthermore, a kernel control region is proposed for monitoring the location and dispersion simultaneously. The average run lengths (ARL) is used to measure the detection performance of the proposed control chart(s). We compare the location and dispersion detection performance of the proposed charts and those of some existing distribution-free charts. An example of service times is used to illustrate the application of the proposed EWMA median and EWMA IQR charts and kernel control region. The proposed charts show superior detection performance compared to the existing distribution-free location and dispersion charts when the shifts in process location and/or dispersion are small. The SS EWMA-Md and DS EWMA-D charts and SS kernel control region are thus recommended. en_US dc.description.tableofcontents 1. Introduction 12. The EWMA-Md Chart 52.1. Construction of the EWMA-Md chart 52.1.1. Determination of the control limits of the EWMA-Md chart 72.2. Detection performance of the EWMA-Md chart 72.3. Performance comparison with existing location control charts 93. The DS EWMA-Md chart 153.1. Construction of the DS EWMA-Md chart 153.1.1. Use simulation to calculate ARL and EN of the DS EWMA-Md chart 173.1.2. Determination of the control limits of the DS EWMA-Md chart 183.2. Detection performance of the DS EWMA-Md chart 193.3. Performance comparison of the proposed single sampling (SS) and DS EWMA-Md charts 214. The EWMA-D Chart 224.1. Construction of the EWMA-D chart 224.1.1. Determination of the control limits of the EWMA-D control chart 244.2. Detection performance of the EWMA-D chart 245. The DS EWMA-D Chart 255.1. Construction of the DS EWMA-D chart 255.1.1. Use simulation to calculate ARL and EN of the DS EWMA-D chart 275.1.2. Determination of the control limits of the DS EWMA-D chart 285.2. Detection performance of the DS EWMA-D chart 295.3. Performance comparison of the proposed SS and DS EWMA-D charts 325.4. Performance comparison with existing dispersion control charts 336. Monitoring Location and Dispersion Simultaneously 366.1. Design of the kernel control region 366.1.1. Kernel density estimation 376.1.2. Determination of the control region based on joint statistics of the EWMA-Md and EWMA-D 386.1.3. Detection performance of the proposed kernel control region 406.1.4. Design of the proposed kernel control chart 406.1.5. Misusing both the EWMA-Md and EWMA-D charts to monitor the process location and/or dispersion. 426.2. DS kernel control region 426.2.1. Design of the DS control region constructed by joint statistics of EWMA-Md and EWMA-D 426.2.2. Detection performance of the DS kernel control region 456.3. Performance comparison with existing control charts 487. Real Example 607.1. Example for single sampling scheme 607.2. Example for double sampling scheme 668. Contamination 748.1. The SS and DS EWMA-Md charts with contamination 748.2. The SS and DS EWMA-D charts with contamination 759. Summary 7910. Reference 80 zh_TW dc.format.extent 3032704 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G1033540051 en_US dc.subject (關鍵詞) 平均連串長度 zh_TW dc.subject (關鍵詞) 不受分配限制 zh_TW dc.subject (關鍵詞) 統計製程管制 zh_TW dc.subject (關鍵詞) 雙次抽樣 zh_TW dc.subject (關鍵詞) Average run length en_US dc.subject (關鍵詞) Distribution-free en_US dc.subject (關鍵詞) Statistical process control en_US dc.subject (關鍵詞) Double sampling en_US dc.title (題名) 中位數和四分位距管制圖設計之研究 zh_TW dc.title (題名) Study on Design of Median and IQR Control Charts for Monitoring Location and Dispersion en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Bakir, S., & Reynolds, M. (1979). A Nonparametric Procedure for Process Control Based on Within-Group Ranking. Technometrics, 21, 175-183. [2] Chacón, J. E., & Duong, T. (2010). Multivariate plug-in bandwidth selection with unconstrained pilot bandwidth matrices. Test, 19(2), 375-398.[3] Chowdhury, S., Mukherjee, A., & Chakraborti, S. (2014). A New Distribution‐free Control Chart for Joint Monitoring of Unknown Location and Scale Parameters of Continuous Distributions. Quality and Reliability Engineering International, 30(2), 191-204. [4] Das, N. (2008). Non-parametric control chart for controlling variability based on rank test. Economic Quality Control, 23(2), 227-242. [5] Daudin, J. J. (1992). Double sampling X̄ charts. Journal of Quality Technology, 24(2), 78-87. [6] Downton, F. (1966). Linear estimates with polynomial coefficients. Biometrika, 53(1/2), 129-141. [7] Ghute, V. (2014). Nonparametric control chart for variability using runs rules. The Experiment, 24(4), 1683-1691. [8] Hawkins, D.M., and Olwell, D.H. (1998), Cumulative Sum Charts and Charting for Quality Improvement, New York: Springer-Verlag.[9] Hawkins, D.M., Qiu, P., and Chang Wook Kang (2003), The changepoint model for statistical process control. Journal of Quality Technology, 35, 355–366.[10] He, D., & Grigoryan, A. (2002). Construction of double sampling s‐control charts for agile manufacturing. Quality and Reliability Engineering International, 18(4), 343-355.[11] He, D., & Grigoryan, A. (2003). An improved double sampling s chart. International Journal of Production Research, 41(12), 2663-2679. [12] Hu, F.-S. (2015). Design of a Control Region for Monitoring Joint Location and Dispersion. [13] 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.[14] Jones, M. A., & Steiner, S. H. (2012). Assessing the effect of estimation error on risk-adjusted CUSUM chart performance. International Journal for Quality in Health Care, 24(2), 176-181.[15] Khoo, M. B. (2005). A control chart based on sample median for the detection of a permanent shift in the process mean. Quality engineering, 17(2), 243-257. [16] Lepage, Y. (1971). A combination of Wilcoxon`s and Ansari-Bradley`s statistics. Biometrika, 58(1), 213-217. [17] Liu, L., Tsung, F., & Zhang, J. (2014). Adaptive nonparametric CUSUM scheme for detecting unknown shifts in location. International Journal of Production Research, 52(6), 1592-1606. [18] Liu, R. Y., & Tang, J. (1996). Control charts for dependent and independent measurements based on bootstrap methods. Journal of the American Statistical Association, 91(436), 1694-1700. [19] Lucas, J. M., & Saccucci, M. S. (1990). Exponentially weighted moving average control schemes: properties and enhancements. Technometrics, 32(1), 1-12. [20] McCracken, A., & Chakraborti, S. (2013). Control charts for joint monitoring of mean and variance: an overview. Quality Technology & Quantitative Management, 10(1), 17-36.[21] Montgomery, D. C. (2009). Statistical quality control (Vol. 7): Wiley New York.[22] Mood AM. (1954). On the asymptotic efficiency of certain nonparametric two-sample tests. Annals of Mathematical Statistics 1954; 25: 514-522.[23] Mukherjee, A., & Chakraborti, S. (2012). A Distribution‐free Control Chart for the Joint Monitoring of Location and Scale. Quality and Reliability Engineering International, 28(3), 335-352. [24] Nelson, L. S. (1963). Tables for a precedence life test. Technometrics, 5(4), 491-499..[25] Nelson, L. S. (1993) Tests on early failures: the precedence life test. Journal of quality technology, 25(2), 140-143.[26] Page, E. (1954). Continuous inspection schemes. Biometrika, 41(1/2), 100-115.[27] Parzen, E. (1962). On estimation of a probability density function and mode. Annals of Mathematical Statistics 33: 1065–1076.[28] Rosenblatt, M. (1956). Remarks on some nonparametric estimates of a density function. Annals of Mathematical Statistics 27: 832–837[29] Shewhart, W. A. (1931). Economic control of quality of manufactured product: ASQ Quality Press.[30] Siegel, S., & Tukey, J. W. (1960). A nonparametric sum of ranks procedure for relative spread in unpaired samples. Journal of the American Statistical Association, 55(291), 429-445.[31] Stromberg, A., Griffith, W., & Smith, M. (2003). Control Charts for the Median and Interquartile Range. In R. Dutter, Filzmoser, P., Gather, U., Rousseeuw, P. (Ed.), International Conference on Robust Statistics 2001-Developments in Robust Statistics (pp. 368-376). Heidelberg GmbH: Springer-Verlag Berlin.[32] Sukhatme, B. V. (1957). On certain two-sample nonparametric tests for variances. The Annals of Mathematical Statistics, 28(1), 188-194.[33] Wu, C. F. (1990). On the asymptotic properties of the jackknife histogram. The Annals of Statistics, 1438-1452. [34] Yang, L., Pai, S., & Wang, Y. R. (2010). A novel CUSUM median control chart. Paper presented at the Proceedings of International Multiconference of Engineers and Computer Scientists.[35] Yang, S. F. (2013). Using a new VSI EWMA average loss control chart to monitor changes in the difference between the process mean and target and/or the process variability. Applied Mathematical Modelling, 37(16), 7973-7982. [36] Yang, S. F., & Arnold, B. C. (2014). A Simple Approach for Monitoring Business Service Time Variation. The Scientific World Journal, 2014, 238719. doi:10.1155/2014/238719[37] Yang, S. F., & Cheng, S. W. (2011). A new non‐parametric CUSUM mean chart. Quality and Reliability Engineering International, 27(7), 867-875. [38] Yang, S. F., Cheng, T. C., Hung, Y. C., & W Cheng, S. (2012). A new chart for monitoring service process mean. Quality and Reliability Engineering International, 28(4), 377-386. [39] Zhang, G. (2014). Improved R and s control charts for monitoring the process variance. Journal of Applied Statistics, 41(6), 1260-1273. doi:10.1080/02664763.2013.864264[40] Zou, C., & Tsung, F. (2010). Likelihood ratio-based distribution-free EWMA control charts. Journal of Quality Technology, 42(2), 174. zh_TW
