系統識別號 | U0002-1607201818385400 |
---|---|
DOI | 10.6846/TKU.2018.00449 |
論文名稱(中文) | 在偏常態下加速破壞衰退試驗的貝氏方法 |
論文名稱(英文) | Bayesian Methods for Skew-Normal Accelerated Destructive Degradation Test |
第三語言論文名稱 | |
校院名稱 | 淡江大學 |
系所名稱(中文) | 數學學系數學與數據科學碩士班 |
系所名稱(英文) | Master's Program, Department of Mathematics |
外國學位學校名稱 | |
外國學位學院名稱 | |
外國學位研究所名稱 | |
學年度 | 106 |
學期 | 2 |
出版年 | 107 |
研究生(中文) | 陳奕汝 |
研究生(英文) | I-Ju Chen |
學號 | 605190171 |
學位類別 | 碩士 |
語言別 | 繁體中文 |
第二語言別 | |
口試日期 | 2018-06-26 |
論文頁數 | 46頁 |
口試委員 |
指導教授
-
蔡志群
委員 - 林千代 委員 - 吳裕振 委員 - 蔡志群 |
關鍵字(中) |
加速破壞衰變試驗 偏常態分配 最大概似估計法 貝氏方法 M-H 演算法 |
關鍵字(英) |
Accelerated Destructive Degradation Test Skew-Normal distribution Maximum likelihood estimation Bayesian Methods Metropolis-Hasting algorithm |
第三語言關鍵字 | |
學科別分類 | |
中文摘要 |
世界邁入高科技時代,高品質和高可靠度產品成為市場主流,然而可靠度和 商品的壽命型態息息相關。在產品之品質特徵值量測過程中,需要對測試產品進 行破壞,並且提高環境應力,才能量測到其品質特徵值,此試驗稱為加速破壞衰 變試驗。林姿吟 (2013) 建構一測量誤差服從偏常態分配的非線性加速破壞衰變 模型。然而其產品第 p 百分位數壽命壽命之 95 %信賴區間過寬,故本文將利用 貝氏方法來估計模型參數,使得模型參數與產品第 p 百分位數壽命之 95 %信賴 區間有效縮短。針對聚合物材料資料,先以一偏常態加速破壞衰變模型描述產品 衰變路徑,分別利用最大概似估計法,與貝氏方法估計模型未知參數,並探討其 壽命資訊。貝氏方法分別使用給定有訊息先驗分配,和無訊息先驗分配之 M-H 演 算法 (Metropolis-Hasting algorithm) 來估計模型參數,接著進行模擬分析比較三 種估計方法,並利用偏差、均方根誤差及覆蓋機率等準則,判定哪一估計方法較 為精準。模擬結果可知使用有訊息先驗分配之估計方法,能有效縮短產品第 p 百 分位數壽命之 95 %信賴區間,且此估計方法相較於最大概似估計法及給定無訊 息先驗分配之貝氏方法都較為精準。 |
英文摘要 |
The accelerated destructive degradation test (ADDT) provided an effective way to assess the reliability information of the highly reliable products whose quality characteristics degraded over time, and can be taken only once on each tested unit during the measurement process. Motivated by a polymer data, Lin (2013) proposed a nonlinear ADDT model with measurement error that follows a skew-normal distribution, and derived the analytical expressions for the product's lifetime distribution. However, the 95% confidence interval of the product's 100pth percentile is not precision. Hence we used Bayesian approach improve the provision of the estimation. More specifically speaking, this article used Metropolis-Hasting algorithm to estimate the parameters of the model, and obtain the posterior credible interval. Finally, a simulation study was conducted to compare the precision of the maximum likelihood and Bayesian estimations. |
第三語言摘要 | |
論文目次 |
第一章 緒論 1 1.1 前言 1 1.2 文獻探討 3 1.2.1 非破壞衰退模型 3 1.2.2 破壞衰退模型 4 1.2.3 偏常態分配 5 1.2.4 貝氏方法 7 1.3 研究動機與目的 9 1.4 研究架構 11 第二章 問題描述 13 第三章 模型參數估計方法 15 3.1 最大概似估計法 15 3.2 貝氏方法 16 3.2.1 蒙地卡羅.馬可夫鏈 17 3.2.2 有資訊先驗分配 19 3.2.3 無資訊先驗分配 22 第四章 實例與模擬 25 4.1 參數估計 25 4.1.1 最大概似估計 25 4.1.2 有資訊先驗分配 27 4.1.3 無資訊先驗分配 29 4.2 模擬分析 31 第五章 結論及後續研究 37 附錄 39 參考文獻 44 |
參考文獻 |
[1] Arellano, R. B. and Azzalini, A. (2013). “The centred parameterization and related quantities of the skew-t distribution,” Journal of Multivariate Analysis, vol. 113, 73–90. [2] Azzalini, A. (1985). “A class of distributions which includes the normal ones,” Scandinavian Journal of Statistics, vol. 12, 171-178. [3] Azzalini, A. and Arellano, R. B. (2013). “Maximum penalized likelihood estimation for skew-normal and skew- t distributions,” Journal of Statistical Planning and Inference, vol. 143, 419–433. [4] Azzalini, A. and Capitanio, A. (2014). The Skew-Normal and Related Families. Cambridge, U.K.: Cambridge Univ. Press. [5] Azzalini, A. and Genton, M. G. (2008). “Robust likelihood methods based on the skew-t and related distributions,” International Statistical Review, vol. 76, 106–129. [6] Boulanger, M. and Escobar, L. A. (1994). “Experimental design for a class of accelerated degradation tests,” Technometrics, vol. 36, 260-272. [7] Carey, M. B. and Koenig, R. H. (1991). “Reliability assessment based on accelerated degradation,” IEEE Transactions on Reliability, vol. 40, 499-506. [8] Chaloner, K. and Verdinelli, I. (1995). “Bayesian experimental design: A review,” Statistical Science, vol. 10, 273–304. [9] Clyde, M., Müller, P. and Parmigiani, G. (1995). “Optimal design for heart defibrillators,” in Case Studies in Bayesian Statistics 2, C. Gatsonis, J. Hodges, R. E. Kass, and N. Singpurwalla, Eds. New York: Springer-Verlag, 278–292. [10] Eling, M. (2012). “Fitting insurance claims to skewed distributions: Are the skew-normal and skew-student good models ? ,” Insurance: Mathematics and Economics, vol. 51, 239–248. [11] Escobar, L. A., Meeker, W. Q., Kugler, D. L. and Kramer, L. L. (2003). “Accelerated destructive degradation tests: data, models, and analysis,” Chapter 21 in Mathematical and Statistical Methods in Reliability, Lindqvist, B. H. and Doksum, K. A., Editors, River Edge, NJ: World Scientific Publishing Company. [12] Genton, M. G. (2004). Skew-Elliptical Distributions and Their Applications: A Journey Beyond Normality. Boca Raton, FL, USA: Chapman & Hall/CRC, Edited Volume. [13] Gómez, H. W. and Salinas, H. S. (2010). “Information matrix for generalized skew-normal distributions,” Proyecciones Journal of Mathematics, vol. 29, 83-92. [14] Gupta, R. C. and Brown, N. (2001). “Reliability studies of the skew-normal distribution and its application to a strength- stress model,” Communications in Statistics - Theory and Methods, vol. 30, 2427-2445. [15] Hamada, M., Martz, H. F., Reese, C. S. and Wilson, A. G. (2001). “Finding near-optimal bayesian experimental designs via genetic algorithms,” The American Statistician, vol. 55, 175–181. [16] Henze, N. (1986). “A probabilistic representation of the skew-normal distribution,” Scandinavian Journal of Statistics, vol. 13, 271-275. [17] Jafari, H. and Hashemi, R. (2011). “Optimal designs in a simple linear regression with skew-normal distribution for error term,” Applied Mathematics, vol. 1, 65-68. [18] Jeng, S. L., Huang, B. Y. and Meeker, W. Q. (2011). “Accelerated destructive degradation tests robust to distribution misspecification,” IEEE Transactions on Reliability, vol. 60, 701-711. [19] Meeker, W. Q. and Escobar, L. A. (1998). Statistical Methods for Reliability Data. New York: John Wiley & Sons. [20] Monti, A. C. (2003). “A note on the estimation of the skew normal and the skew exponential power distributions,” Metron International Journal of Statistics, LXI, 205-219. [21] Nelson, W. (1981). “Analysis of performance degradation data from accelerated tests,” IEEE Transactions on Reliability, vol. 30, 149-155. [22] Nelson, W. (1990). Accelerated Testing: Statistical Models, Test Plans, and Data Analysis. New York: John Wiley & Sons. [23] Peng, C. Y. and Tseng, S. T. (2009). “Mis-specification analysis of linear degradation models,” IEEE Transactions on Reliability, vol. 58, 444-455. [24] Peng, C. Y. and Tseng, S. T. (2013). “Statistical lifetime inference with skew-Wiener linear degradation models,” IEEE Transactions on Reliability, vol. 62, 338-350. [25] Polson, N. G. (1993). “A Bayesian perspective on the design of accelerated life tests,” Advances in Reliability, A. P. Basu, Ed., New York: Elsevier, 321–330. [26] Shi, Y. and Meeker, W. Q. (2012). “Bayesian methods for accelerated destructive degradation test planning,” IEEE Transactions on Reliability, vol. 61, 245-253. [27] Shi, Y., Meeker, W. Q. and Escobar, L. A. (2009). “Accelerated destructive degradation test planning,” Technometrics, vol. 51, 1-13. [28] Tsai, C. C., Lin, C. T., and Balakrishnan, N. (2017). “A Survey of the Modeling and Application on Non-destructive and Destructive Degradation Tests,” 105-124, Chapter 6, Statistical Modeling for Degradation Data, Springer. [29] Tsai, C. C., Tseng, S. T., Balakrishnan, N. and Lin, C. T. (2013). “Optimal design for accelerated destructive degradation test,” Quality Technology and Quantitative Management, vol. 10, 263-276. [30] Yang, G. (2007). Life Cycle Reliability Engineering. Hoboken, New Jersey: John Wiley & Sons. [31] Yu, H. F. (2003). “Designing an accelerated degradation experiment by optimizing the estimation of the percentile,” Quality and Reliability Engineering International, vol. 19, 197-214. [32] Zhang, Y. and Meeker, W. Q. (2006). “Bayesian methods for planning accelerated life tests,” Technometrics, vol. 48, 49–60. [33] 林姿吟 (2013). ⟨ 偏常態量測誤差模型下之加速破壞衰變試驗 ⟩,淡江大學數學學系數學所碩士論文。 |
論文全文使用權限 |
如有問題,歡迎洽詢!
圖書館數位資訊組 (02)2621-5656 轉 2487 或 來信