型二設限柯西分配之貝氏分析-使用JAGS軟體

Bayesian Analysis of Cauchy Distribution Under Type II Censoring Using JAGS

鄭智壕(CHIH-HAO CHENG)

指導教授 ： 林余昭

中原大學/理學院/應用數學系/碩士(2024年)

https://doi.org/10.6840/cycu202400136

摘要

貝氏統計方法在現代統計學中扮演著解決複雜問題的重要角色。JAGS（Just Another Gibbs Sampler）作為一個開源的貝氏統計建立模型、參數模擬與計算的工具，它在處理各種類型的統計資料方面表現優異且方便，因此吸引了不少的使用者。
在現代資訊發達的時代，型二設限資料是一類常見的數據，結合觀測對某些變數的限制。這類資料廣泛應用於工業加速試驗分析、長期追蹤研究和醫學臨床試驗。JAGS則提供了一個強大的平台，用於建立和估計複雜的貝氏模型，有助於精確預測和推斷，同時處理設限資料的挑戰。
本篇論文強調了JAGS在處理型二設限資料的價值，不僅為統計學家和研究人員提供了強大工具，還擴展了貝氏統計方法在現代社會中的應用範疇。這有助於解決複雜問題，特別是那些包含限制性條件的問題。

關鍵字

Just Another Gibbs Sampler ； 馬可夫鏈蒙地卡羅 ； 型二設限資料

並列摘要

Bayesian statistical methods play a crucial role in addressing complex issues in statistics. JAGS (Just Another Gibbs Sampler), an open-source Bayesian statistical modeling, parameter simulation and calculation tool, excels in handling various statistical data. Therefore, it is popular in Bayesian reasoning.
In the modern era, full of rich information, Type II censored data is a common type of data that combines observed outcomes with restrictions on certain variables. Such data is widely used in industrial accelerated test analysis, long-term tracking studies and medicine clinical trials. JAGS provides a robust platform for constructing and estimating complex Bayesian models, facilitating accurate predictions and inferences.
This research illustrates how to analyze Type II data using JAGS. It not only provides statisticians and researchers with a powerful tool but also extends the applications of Bayesian statistical methods in modern society. This study provides a way to solve complex data with restrictive conditions.

並列關鍵字

Just Another Gibbs Sampler ； Markov Chain Monte Carlo ； Type II Censored Data

參考文獻

[1]. Box, G. E., & Tiao, G. C. (2011). Bayesian inference in statistical analysis. John Wiley & Sons.

[2]. Casella, G., & George, E. I. (1992). Explaining the Gibbs sampler. The American Statistician, 46(3), 167-174.

[3]. Chib, S., & Greenberg, E. (1995). Understanding the metropolis-hastings algorithm. The american statistician, 49(4), 327-335.

[4]. Denwood, M. J. (2016). runjags: An R package providing interface utilities, model templates, parallel computing methods and additional distributions for MCMC models in JAGS. Journal of statistical software, 71, 1-25.

[5]. Geman, S., & Geman, D. (1984). Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on pattern analysis and machine intelligence, (6), 721-741.