DO NOT WEIGHT FOR HETEROSCEDASTICITY IN NONPARAMETRIC REGRESSION
作者:
M.C. Jones,
期刊:
Australian Journal of Statistics
(WILEY Available online 1993)
卷期:
Volume 35,
issue 1
页码: 89-92
ISSN:0004-9581
年代: 1993
DOI:10.1111/j.1467-842X.1993.tb01315.x
出版商: Blackwell Publishing Ltd
关键词: Bias reduction;kernel regression;local variability
数据来源: WILEY
摘要:
SummaryThe potential role of weighting in kernel regression is examined. The concept that weighting has something to do with heteroscedastic errors is shown to be false. However, weighting does affect bias, and ways in which this might be exploited are indicated.
点击下载:
PDF
(202KB)
返 回