Fuzzy-weighted bootstrap estimation in semi-parametric model

doi:10.1080/09720510.2003.10701092

淡江大學機構典藏 > 商管學院 > 統計學系暨研究所 > 期刊論文 > Item 987654321/18490

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/18490

題名:	Fuzzy-weighted bootstrap estimation in semi-parametric model
作者:	Tsai, Tzong-ru;Wu, Shuo-jye
貢獻者:	淡江大學統計學系
關鍵詞:	Bootstrap estimation;optimal fuzzy clustering analysis method;ordinary least squares estimation;percentile interval estimation;semi-parametric model
日期:	2003-06-14
上傳時間:	2009-09-01 16:09:12 (UTC+8)
出版者:	TARU Publications
摘要:	Many statisticians use a semi-parametric model to examine the relationship between explanatory and response variables. In practice, a data set often contains outliers and, hence the traditional estimation methods may not be appropriate. Wu et al. (1996) provided a fuzzy-weighted estimator to reduce the influence of outliers and they discussed its asymptotic properties. However, the test performance in small sample is not discussed. In this paper, a percentile interval estimation method based on fuzzy-weighted bootstrap samples is provided and we call the improved percentile interval estimation method. We show that the fuzzy-weighted bootstrap estimator and the fuzzy-weighted estimator have the same asymptotic properties. In addition, the proposed method can reduce the influence of outliers efficiently when we make inference about the scaled regression coefficient in small sample. Hence, we provide an alternative estimation method to make inference when sample size is small.
關聯:	Journal of statistics and management systems 6(3), p.443-461
DOI:	10.1080/09720510.2003.10701092
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	大小	格式	瀏覽次數
index.html	0Kb	HTML	243	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.

TAIR相關文章

資料載入中.....