Robust Regression Based on Infinitesimal Neighbourhoods
Robust Regression Based on Infinitesimal Neighbourhoods
复制标题
基于无穷小邻域的鲁棒回归
DOI：
--
复制
发表时间：
1984
期刊：
影响因子：
--
通讯作者：
P. Bickel
中科院分区：
文献类型：
--
作者：
P. Bickel
本文研究了一般正态回归模型中的抗差估计问题。这个框架是Bickel（1981）的框架。作为特例，我们得到了Huber（1982），Krasker-Hampel（1980）和Krasker-Welsch（1982）的解以及一些新的方法。我们的计算表明，这些估计的最优性比Krasker和Welsch建议的更有限。
We study robust estimation in the general normal regression model with random carriers permitting small departures from the model. The framework is that of Bickel (1981). We obtain solutions of Huber (1982), KraskerHampel (1980) and Krasker-Welsch (1982) as special cases as well as some new procedures. Our calculations indicate that the optimality properties of these estimates are more limited than suggested by Krasker and Welsch.