首页   按字顺浏览 期刊浏览 卷期浏览 Two Robust Alternatives to Least-Squares Regression
Two Robust Alternatives to Least-Squares Regression

 

作者: RichardW. Hill,   PaulW. Holland,  

 

期刊: Journal of the American Statistical Association  （Taylor Available online 1977）
卷期: Volume 72, issue 360  

页码: 828-833

 

ISSN:0162-1459

 

年代: 1977

 

DOI:10.1080/01621459.1977.10479965

 

出版商: Taylor & Francis Group

 

关键词: Robust regression;Mestimators;One-step sine estimator;L1 estimator;Monte Carlo

 

数据来源: Taylor

 

摘要:

We give Monte Carlo results on the performance of two robust alternatives to least-squares regression estimation—least-absolute residuals and the one-step sine estimator. We show how to scale the residuals for the sine estimator to achieve nearly constant efficiency for the normal distribution across various choices of the design matrix. We compare the two estimators to least squares for nine scale-contaminated normal distributions.

 

点击下载:  PDF (603KB)



返 回