請使用永久網址來引用或連結此文件:
https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/90193
|
| 題名: | Assessment of Various FDR Procedures |
| 作者: | Kao, Tzu-Hui;Chen, Yi-Ju;Lin, Kuo-Chin |
| 貢獻者: | 淡江大學統計學系 |
| 關鍵詞: | FDR;Multiple testing;Power;Type I error rate |
| 日期: | 2011-11 |
| 上傳時間: | 2013-06-04 16:35:53 (UTC+8) |
| 出版者: | ICIC International |
| 摘要: | In high dimensional studies, controlling the false discovery rate (FDR) has become an important issue where the multiplicity is a problem. Traditionally, familywise error rate (FWER) is used to control the overall type I error rate in the application of multiple comparisons. However, when many of null hypotheses are false, FWER tendsto be more conservative and has less power. To improve the drawbacks of FWER, an innovative approach based on FDR can be used. The purpose of this article is to compare the performance of current step-up and step-down procedures and detect the merits and flaws of these procedures. In addition, the comparison of those procedures is illustrated by an example. |
| 關聯: | ICIC Express Letters 5(11), pp.4007-4012 |
| 顯示於類別: | [統計學系暨研究所] 期刊論文
|
文件中的檔案:
| 檔案 |
描述 |
大小 | 格式 | 瀏覽次數 |
|---|
| Assessment of various FDR procedures.pdf | | 1522Kb | Adobe PDF | 2 | 檢視/開啟 | | index.html | | 0Kb | HTML | 85 | 檢視/開啟 |
|
在機構典藏中所有的資料項目都受到原著作權保護.
|