| 研究生: |
羅文宜 |
|---|---|
| 論文名稱: |
具有訊息的遺失資料計算方法之比較 |
| 指導教授: | 姜志銘 |
| 學位類別: |
碩士
Master |
| 系所名稱: |
理學院 - 應用數學系 Department of Mathematical Sciences |
| 論文出版年: | 2005 |
| 畢業學年度: | 93 |
| 語文別: | 中文 |
| 論文頁數: | 62 |
| 中文關鍵詞: | 遺失資料 、貝氏方法 、準貝氏法 、吉氏取樣器 |
| 相關次數: | 點閱:165 下載:49 |
| 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 |
對於處理部份區分或是失去部分訊息資料的類別抽樣的問題,在許多領域裡皆有許多的應用。貝氏方法雖可處理這類問題,但是貝氏方法對這類問題的計算相當耗時,因此對於這種問題的後驗估計,Jiang (1995) 及 Jiang and Dickey (2005) 提出quasi-Bayes方法,Jiang and Ko (2004)利用Gibbs sampler來近似(approximate)這些後驗估計值。但是這兩種近似方法的優劣,因為貝氏方法計算上的困難,一直沒有任何文章作這方面的比較,本文突破計算上的某些限制,在小樣本時,對這兩種近似方法的近似度(相對於真正的貝氏值)作比較,進一步探討使用兩種比較方法的優劣。
1 簡介........................................................3
2 計算方法的介紹..............................................4
2.0 貝氏法在不完整多元伯努利上的應用.........................4
2.1 準貝氏法在不完整多元伯努利上的應用.......................8
2.2 吉氏取樣器..............................................11
2.2.1 吉氏取樣器的介紹.....................................11
2.2.2 簡單的收斂說明.......................................13
2.2.3 吉氏取樣器在不完整多元伯努利上的應用.................15
3 Fortran程式................................................18
3.1 迴圈單一化..............................................18
3.2 溢位....................................................21
4 準貝氏法與吉氏取樣器的比較結果.............................27
5 結論.......................................................41
A 兩種比較方法之平均相對誤差的折線圖.........................44
B 兩種比較方法在觀察值order不同時估計值的MSE折線圖...........48
C Fortran 90程式.............................................50
Casella. G., and George, E. I. (1992), "Explaining the Gibbs sampler," The American Statistician, 46, 167-174.
Dickey, J.M., Jiang, T. J., and Kadane, J. B. (1987), "Bayes Methods for Censored Categorical Data," Journal of the American Statistical Association, 85, 398-409.
Gelfand, A. E., Smith, A. F. M. (1990), "Sampling-Based Approaches to Calculating Marginal Densities," Journal of the American Statistical Association, 85, 398-409.
Hastings, W. K. (1970), "Monte Carlo Sampling Methods Using Markov Chains and their Application," Biometrika, 57, 97-109.
Jiang, T. J. (1995), "Quasi-Bayes Sequential Method For Categorical Data Under Informative Censoring," Technical Report, 1995-02, Dept. of Mathematical Sciences, National Chengchi University.
Jiang, T. J., and Dickey, J. M. (2005), "Quasi-Bayes Methods for Categorical Data Under Informative Censoring," to be published.
Jiang, T. J., Kadane, J. B., and Dickey, J. M. (1992), "Computation of Carlson's Multiple Hypergeometric Function R for Bayesian Applications," Journal of Computational and Graphical Statistics, 1, 231-251.
Jiang, T. J., and Ko, Li-Wen (2004), "The Gibbs sampler for Bayesian Analysis on Censored Categorical Data," 2004 Proceeding of the section on Bayesian Statistical Science of the American Statistical Association, 97-103.
Karson, M. J., and Wrobleski, W. J. (1970), "A Bayesian Analysis of Binomial Data With a Partially Informative Category," in Proceedings of the Business and Economic Statistics Section, American Statistical Association, 532-534.
Geman, S., and Geman, D. (1984), "Stochastic Relation, Gibbs Distribution and the Bayesian Restortion of Image," IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 721-741.
汪為開(1995), "失去部分訊息而有價值的類別資料依循序程序處理之計算方法"碩士論文-國立政治大學應用數學系研究所.
柯力文(2003), "準貝氏法與吉氏取樣器在處理失去部分訊息資料上的比較" 碩士論文-國立政治大學應用數學系研究所.