透過您的圖書館登入
IP:3.14.15.94
  • 學位論文

逐步型一區間設限資料之廣義指數分配的貝氏分析

Bayesian Analysis of Progressive Type I Interval Censored Data Under General Exponential Distribution

指導教授 : 鄭子韋 林余昭

摘要


此篇論文中主要使用 R2WinBUGS套件來分析以廣義指數分配下的逐步型一區間設限。一開始會使用 R跑出的樣本資料,而用 WinBUGS來進行分析樣本資料進而估計參數。之後將 R與 WinBUGS做結合。我們使用 R2WinBUGS來進行分析參數。 WinBUGS相較於 R統計軟體,操作上較為繁雜,而且對於資料操控與分析結果的深入分析並不夠好。故本篇論文主要使用 R2WinBUGS來進行分析。 R2WinBUGS是 R軟體內的軟體元件包之一,安裝此軟件後,要使用 WinBUGS來分析資料,只需要使用 R統計軟體內編寫程式即可。在本篇論文中,會使用 WinBUGS程式碼的操作與 R軟體內的 R2WinBUGS進行比較。 本篇論文的最後會使用 R軟體的迴圈程式碼,進行多次的 WinBUGS的資料分析。

並列摘要


WinBUGS is a commonly used statistical software for Bayesian statistician to execute the Markov chain Monte Carlo method via Metropolis-Hastings algorithm in simple statistical programming codes. However, the operation of such software is not friendly and its outputs are limited. The Bayesian analysis of type I interval censored data from General Exponential distribution was done in Lin and Lio (2012). Yet, this research takes the advantage of data manipulation function of the popular statistical software R and the simple but powerful statistical ability of Bayesian tool WinBUGS to do statistical estimation of type I interval censored data from General Exponential distribution. Specifically, we propose to generate progressive type I interval observations in R and analyze these simulated data with R2WinBUGS package that calls WinBUGS in batch mode. The results are then passed back to R for further analysis. Finally, the simulation studies are done for 500 times to calculate the standard error of the our proposed algorithm.We can see that the results seems satisfactory as expected. Overall, the research apply R2WinBUGS package to analyze the type I interval censoring scheme.

參考文獻


2. 張志賢 (2013) 型一區間設限廣義指數分配資料之WinBUGS貝氏分析 碩士論文 中原大學應用數學系。
3. 黃韋勝 (2013) 型一區間設限韋伯分配資料之WinBUGS貝氏分析 碩士論文 中原大學應用數學系。
1. 許文志 (2010) 逐步型一區間設限資料的貝氏分析 碩士論文 中原大學應用數學系。
6. Gupta, R. D. and Kundu, D. (2001a) “Exponentiated exponential distribution: An alternative to gamma and Weibull distributions”. Biometrical Journal, 43:117-130.
7. Gupta, R. D. and Kundu, D. (2001b) “Generalized Exponential Distributions: different method of estimations”. Journal of Statistical Computation and Simulation, 69:315-338.

延伸閱讀