透過您的圖書館登入
IP:216.73.216.116
  • 學位論文

隨機移除之一般化型二逐步設限下對雙參數Burr-XII分配和一個新的具有浴缸型或遞增失敗率函數之雙參數壽命分配的統計推論

Statistical inferences for the two parameters Burr-XII distribution and a new two parameters lifetime distribution with bathtub shape or increasing failure rate function under general type II progressive censoring with random removals

指導教授 : 吳淑妃

摘要


在許多自然科學及工業生產的研究中,生物或是產品的壽命往往都是研究的重點。現實中常會因為時間、人力和金錢的限制或成本的考量而無法取得完整的樣本資料,而在產品壽命檢測的實驗中,各種設限的方法都是為了節省時間與成本,一般化型二逐步設限就是其中的一種。 在工業生產中,產品會因疲勞或劣化而故障時,其壽命模式會呈現單峰型的故障率曲線模式,所以Burr XII分配是適合的。而有些產品的故障率函數會成浴缸型(bathtub shape)的曲線模式,所以具有浴缸型或遞增失敗率函數分配是適合的。 在本文中我們所要探討的主題就是在隨機移除之一般化型二逐步設限的方法下所獲得之有序樣本 經過適當的轉換,可得到一組來自標準指數分配且互相獨立的樣本 ,接著利用此組樣本形成 個樞紐量,和我們所提出的一組新的樞紐量,對來自於雙參數Burr-XII分配和具有浴缸型或遞增失敗率函數之雙參數壽命分配的形狀參數做假設檢定和信賴區間,以及建立雙參數之聯合信賴區域。最後利用電腦模擬的方法,在不同的 下找出檢定力最好以及信賴區間長度最短和聯合信賴區域面積最小的樞紐量。結果顯示,我們所提出的新樞紐量皆有最佳的表現。

並列摘要


Studies in the lifetime of the products are often the main research topics in industrial experiment. Due to the restriction of time, cost and material, censoring arises. There are several types of censoring schemes and the General Type II Progressive censoring scheme is one of those. When the failure factor of the product is fatigue or aging, Burr XII distribution with unimodal failure rate function will be more appropriate. When the hazard function of the product has bathtub shape, Bathtub distribution is more appropriate. Therefore, the interval estimations of two parameters and the hypothesis testing under General Type II progressive censoring with random removals are proposed in this research. We proposed a set of new pivotal quantities with new distribution to be compared with some other pivotal quantities with F distribution in this paper. After the simulation studies, the new pivotal quantities have better performance based on the criteria of minimum confidence length or area for the interval estimation and the largest power for the Hypothesis test.

參考文獻


[1] Aggarwala, R. & Balakrishnan, N. (1998) Some properties of progressive censored order statistics from the Pareto distribution with applications to inference, IEEE Transactions on Reliability, 65, 356-367.
[2] Ali, Mousa, M. A. M. and Jaheen, Z. F. (2002) Bayesian prediction for progressively censored data from burr model, Statistical papers, 43, 587-593.
[3] Arturo J. (2004) On estimating exponential parameters with general type II progressive censoring, Journal of Statistical planning and inference, 121, 135-147.
[4] Balakrishnan, N., Sandhu, R. A. (1996) Best linear unbiased and Maximum likelihood estimation for Exponential distributions under general progressive Type II censored samples, The Indian Journal of Statistics, 58, 1, 1-9.
[5] Balakrishnan, N. & Aggarwala, R. (2000) Progressive censoring:Theory, Methods and Applications (Boston, Birkhauser).

被引用紀錄


周啟翔(2007)。在一般化型二逐步設限下使用新樞紐量對具有浴缸型或遞增失敗率函數之雙參數壽命分配與對數常態分配做統計推論〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2007.00084
胡耿豪(2006)。在設限樣本下具有浴缸型或遞增的故障率函數的壽命分配之形狀參數的新加權平均數檢定與區間估計〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2006.00798
廖佩怡(2006)。一般化型二逐步設限下對雙參數Gompertz分配與雙參數極值分配的統計推論〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2006.00622

延伸閱讀