none｜國立中央大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	何致晟 Zhisheng He
論文名稱：	Parametric likelihood inference with censored survival data under the COM-Poisson cure models
指導教授：	江村剛志
口試委員:
學位類別：	碩士 Master
系所名稱：	理學院 - 統計研究所 Graduate Institute of Statistics
論文出版年：	2017
畢業學年度：	105
語文別：	英文
論文頁數：	73
中文關鍵詞：	廣義伽瑪分佈、最大期望演算法、邏輯鏈接、牛頓-拉弗森演算法、存活分析、韋伯分佈
外文關鍵詞：	Generalized gamma distribution, EM algorithm, Logistic link, Newton-Raphson algorithm, Survival analysis, Weibull distribution
相關次數：	點閱：14 下載：0
分享至:	分享至facebook 分享至twitter

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

對設限存活資料(censored survival data)分析，Rodrigues等(2009)提出用Conway-Maxwell-Poisson (COM-Poisson)分佈為治愈模型(cure rate model)。對COM-Poisson治愈模型之特例——伯努利治愈模型(Bernoulli cure rate model)，考慮使用不同之運算演算法，以最大概似估計法(maximum likelihood estimation)得參數之估計值。據Balakrishnan與Pal於2016以韋伯分佈(Weibull distribution)及於2015以廣義伽瑪分佈(generalized gamma distribution)，假設為其壽命分佈(lifetime distribution)。進而導出之評分函數(score function)與黑塞矩陣(Hessian matrix)，用以牛頓-拉弗森演算法(Newton-Raphson algorithm)及最大期望演算法(EM algorithm)。模擬為分析比較此二種演算法之表現。末了，實際資料分析作詳加闡明此方法模型。

Rodrigues et al. (2009) proposed the Conway-Maxwell-Poisson (COM-Poisson) distribution as a model for a cure rate in censored survival data. We consider computational algorithms for maximum likelihood estimation under the Bernoulli cure rate model, a special case of the COM-Poisson cure rate model. The Weibull distribution (Balakrishnan and Pal 2016) and the generalized gamma distribution (Balakrishnan and Pal 2015) are considered as lifetime distributions. We obtain all the expressions of the score function and Hessian matrix to perform the Newton-Raphson and EM algorithms. Simulations are conducted to compare the performance between the EM algorithm and Newton-Raphson algorithms. Finally, a real data is analyzed to illustrate the methods.

Contents
Chapter 1 Introduction ………………………………………...…………………………….1
Chapter 2 Background ………………………………………………………………………3
2.1 The Conway-Maxwell-Poisson (COM-Poisson) distribution …………………………..3
Example: The Bernoulli distribution …………………………………………….……….4
2.2 Lifetime distributions ………………………………………………………….…..……5
Example 1: The Weibull distribution …………………………………...............………..6
Example 2: The generalized gamma distribution …………………………………...……6
2.3 Long-term survival function ……………………………………………………………8
Chapter 3 Maximum likelihood estimation ………………………………………...………9
3.1 Right-censored data with cure …………………………………………………….…….9
3.2 Log-Likelihood under the Bernoulli cure model …………………………………...….11
Example 1: Weibull lifetime with Bernoulli cure ………………………………..……..12
Example 2: Generalized gamma lifetime with Bernoulli cure ………………………….12
3.3 EM-algorithm …………………………………………………………………....…….13
3.3.1 The complete data likelihood function ……………………………………………13
3.3.2 Cure rate model with Weibull lifetime ……………………………………..……..15
Example: Bernoulli cure rate model with Weibull lifetime ………………………...…..16
3.3.3 Cure rate model with generalized gamma lifetime …………………………….....18
Example: Bernoulli cure rate model with generalized gamma lifetime ………………...19
Chapter 4 Computational algorithms ……………………………………………………..21
4.1 Newton-Raphson algorithm ……………………………………………………….…..21
Example 1: Randomized Newton-Raphson algorithm with Weibull lifetime ………..…21
Example 2: Algorithm with generalized gamma lifetime …………………………..…..23
4.2 EM-algorithm ………………………………………………………………………….24
Example 1: M-step by randomized Newton-Raphson with Weibull lifetime …………..24
Example 2: M-step algorithm with generalized gamma lifetime ……………………….26
4.3 Interval estimation ………………………………………………………………….….27
Chapter 5 Simulation ……………………………………………………………….………30
5.1 simulation design …………………………………………………………………..….30
5.2 Simulation results ……………………………………………………………………..33
Chapter 6 Data analysis …………………………………………………...………………..39
6.1 Tumor metastasis data …………………………………………………………………39
6.2 Model fitting with Bernoulli cure model ……………………………….……………..40
6.2.1 Weibull lifetime ……………………………………………………………….…..40
6.3 Discuss under generalized gamma lifetime ……………………………………….…..45
6.3.1 Covariate with gender ………………………………………………………….....45
6.3.2 Covariate with tumor position …………………………………………………….48
Chapter 7 Conclusion and discussion ……………………………………………..……….52
Reference……………………………………………………………………………….….54
Appendix A …………………………………...……………………………………………..55
Appendix B ………………………………………………………………………………….56
Appendix C  …………………………………………………………………………….……62
Appendix D…………………………………………………………………………………….65

                                

Balakrishnan N, Pal S (2016) Expectation maximization-based likelihood inference for flexible cure rate models with Weibull lifetimes. Statistical Methods in Medical Research. 25(4):1535–1563.
Balakrishnan N, Pal S (2015) An EM algorithm for the estimation of parameters of a flexible cure rate model with generalized gamma lifetime and model discrimination using likelihood- and information-based methods. Computational Statistics. 30: 151-189.
Conway RW and Maxwell WL (1962) A queuing model with state dependent services rates. Journal of Industrial Engineering. 12: 132-136.
Cordeiro GM, Rodrigues J, de Castro M (2012) The exponential COM-Poisson distribution. Statistical Papers. 53(3):653-664.
Emura T, Wang H (2010). Approximate tolerance limits under log-location-scale regression models in the presence of censoring. Technometrics 52(3): 313-323.
Emura T, Wang W (2012) Nonparametric maximum likelihood estimation for dependent truncation data based on copulas. Journal of Multivariate Analysis 110: 171-188.
Emura T, Shiu SK (2016) Estimation and model selection for left-truncated and right-censored lifetime data with application to electric power transformers analysis, Communications in Statistics-Simulation and Computation. 45 (9): 3171-89
EMBL-EBI. (2012) E-GEOD-22138-Expression Data from Uveal Melanoma primary tumors. http://www.ebi.ac.uk/arrayexpress/experiments/E-GEOD-22138/
Hu YH, Emura T (2015) Maximum likelihood estimation for a special exponential family under random double-truncation. Computational Statistics. 30:1199-1229
Ibrahim JG, Chen M-H and Sinha D (2001) Bayesian survival analysis. JASA. 99(468):1202-03.
Knight K (2000) Mathematical statistics. Chapman and Hall, Boca Raton.
Lange K (1995) A gradient algorithm locally equivalent to the EM algorithm. JRSSB. 57:425-437
Rodrigues J, de Castro M, Cancho VG, Balakrishnan N (2009) COM–Poisson cure rate survival models and an application to a cutaneous melanoma data. Journal of Statistical Planning and Inference. 139: 3605–3611.
MacDonald IL (2014) Does Newton–Raphson really fail? Statistical Methods in Medical Research. 23(3): 308-311.
Maller RA, Zhou X (1996) Survival Analysis with Long-Term Survivors, (1st edition). Wiley, Chichester.
McLachlan GJ and Krishman T (2008) The EM algorithm and extensions, (2nd edition), John Wiley & Sons, Hoboken.

簡易檢索 / 詳目顯示

相關論文