研究生: |
黃屏衽 Ping-Ren Huang |
---|---|
論文名稱: |
在多重設限資料下混合型韋伯參數的三種演算法之比較研究 A Study of Three Algorithms for Estimating the Mixture Weibull Parameters with Multiple Censored Data |
指導教授: |
王福琨
Fu-Kwun Wang |
口試委員: |
歐陽超
Chao Ou-Yang 林希偉 Shi-Woei Lin |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 工業管理系 Department of Industrial Management |
論文出版年: | 2013 |
畢業學年度: | 101 |
語文別: | 中文 |
論文頁數: | 53 |
中文關鍵詞: | 混合型韋伯分配 、最大概似估計法 、多重設限資料 、PSO 演算法 、擬牛頓法 、EM演算法 |
外文關鍵詞: | Mixture Weibull distribution, Multiple censored data, Maximum likelihood estimation, PSO algorithm, Quasi-Newton method, EM algorithm |
相關次數: | 點閱:411 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
混合型韋伯分配是可應用於存活分析與可靠度分析的重要統計分配。本論文主要在探討混合型韋伯分配在多重設限資料下,利用最大概似估計法做參數估計,且透過 PSO 演算法、擬牛頓法與 EM 演算法對概似函數進行優化求解。本研究藉由模擬的分析,比較三種演算法參數估計之結果,而我們可以得知利用PSO演算法求得之結果是優於其他兩種演算法。此外,再藉由實際案例來驗證結果是否與模擬結果為一致。
The mixture Weibull distributions can be applied to survival analysis and reliability analysis which is the field of statistical research. In this study we used the maximum likelihood estimation (MLE) to estimate the mixture of two Weibull parameters with multiple censored data via particle swarm optimization (PSO) algorithm, quasi-Newton method and expectation-maximization (EM) algorithm. We used the simulation study to compare the three algorithms. The simulation results showed that the PSO algorithm outperforms the quasi-Newton method and the EM algorithm. Two numerical examples are used to demonstrate the performance of our proposed method.
中文文獻
[1]江峰政,2005。有關EM法於具韋伯之設限資料其參數之估計,國立成功大學碩士論文。
[2]林竹青,2004。年齡縮減之不完全預防維護模型參數估計,私立朝陽科技大學碩士論文。
[3]詹鎬陽,2010。短尾對稱分配之詹森-內曼非顯著區域,私立逢甲大學碩士論文。
英文文獻
[1] Al-Hussaini, E.K., G.R. Al-Dayian, and S.A. Adham, “Mixture of two-component gompertz lifetime model,” Journal of Statistical Computation and Simulation, 67(1), 20-67 (2000).
[2] Antle, C.E., L.J. Bain, and D.R. Thoman, “Inferences on the parameters of the Weibull distribution,” Technometrics, 11(3), 445-460 (1969).
[3] Bain, L.J. and M. Engelhardt, “Statistical Analysis of Reliability and Life-Testing Models,” Marcel Dekker, New York, (1991).
[4] Blischke, W. R. and D.N.P. Murthy, “Product Warranty Handbook,” Marcel Dekker, New York, (2000).
[5] Blischke, W.R. and D.N.P. Murthy, “Product Warranty Handbook,” Marcel Dekker, New York, (2000).
[6] Broyden, C.G., “The convergence of a class of double-rank minimization algorithm,” IMA Journal of Applied Metric Algorithm, 6(1), 76-90 (1970).
[7] Campos, M., R.A. Krohling, and P. Borges, “Particle swarm optimization for inference procedures in the generalized Gamma family based on censored data,” in J. Mehnen et al. (Eds.) Applications of Soft Computing, 58, 411-422 (2009).
[8] Carter, A.D.S., “Mechanical Reliability,” Wiley, New York, (1986).
[9] Clerc, M., “Particle Swarm Optimization,” ISTE Publishing Company, London. (2007).
[10] Cohen, A.C., “Maximum likelihood estimate in the Weibull distribution based on complete and on censored samples,” Technometrics, 7(4), 579-588 (1965).
[11] Dempster, A., N. Laird and D. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” Journal of the Royal Statistical Society, Series B, 39(1), 1-38 (1977).
[12] Fisher, R.A. and L.H.C. Tippett, “Limiting forms of the frequency distribution of the largest or smallest member of a sample”, in R.A. Fisher, Contributions to Mathematical Statistics, John Wiley, New York, (1950).
[13] Fletcher, R., “A new approach to variable metric algorithms,” The Computer Journal, 13(3), 317-322 (1970).
[14] Goldfarb, D., “A family of variable metric methods derived by variational means,” Mathematics of Computation, 24(109), 23-26 (1970).
[15] Jiang, R. and D.N.P. Murthy, “Modeling failure data by mixtures of two Weibull distribution : a graphical approach,” IEEE Transactions on Reliability, 44(3), 477-487 (1995).
[16] Jiang, R., D.N.P. Murthy and P. Ji, “Models involving two inverse Weibull distributions,” Reliability Engineering and System Safety, 73(1), 73-81 (2001).
[17] Kao, J.H.K., “A graphical estimation of mixed Weibull parameters in life-testing of electron tubes,” Technometrics, 1(4), 389-407 (1959).
[18] Keats, J.B., F.P. Lawrence and F.K. Wang, “Weibull maximum likelihood parameter estimates with censored data,” Journal of Quality Technology, 29(1), 105-110 (1997).
[19] Kennedy, J. and R. Eberhart, “Particle Swarm Optimization,” In: Proceedings of the IEEE International Conference Neural Networks, 1942-1948 (1995).
[20] Ling, J. and J. Pan, “A new method for selection of population distribution and parameter estimation,” Reliability Engineering and System Safety, 60(3), 247-55 (1998).
[21] Lui, C. and D.B. Rubin, “The ECME Algorithm : a simple extension of EM and ECM with faster monotone convergence,” Biometrika, 81(4), 633-648 (1994).
[22] McLachlan, G. J. and T. Krishnan, “The EM Algorithm and Extensions,” Wiley,New York, (1997).
[23] Meng, X.L. and D.B. Rubin, “Maximum likelihood estimation via the ECM Algorithm : a general framework,” Biometrika, 80(2), 267-278 (1993).
[24] Menon, M.V., “Estimation of the shape and scale parameter of the Weibull distribution,” Technometrics, 5(2), 175-182 (1963).
[25] Murthy, D.N.P., M. Xie and R. Jiang, “Weibull Models,” Wiley, New York, (2004).
[26] Nelson, W., “Accelerated Testing,” John Wiley, New York, (1990).
[27] R Development Core Team, “R: A Language and Environment for Statistical Computing,” Vienna, Austria: R Foundation for Statistical Computing, (2012).
[28] Shanno, D.F., “Conditioning of quasi-Newton methods for function minimization,” Mathematics of Computation, 24(111), 647-656 (1970).