Inflation of R2in Best Subset Regression
作者:
AlvinC. Rencher,
FuCeayong Pun,
期刊:
Technometrics
(Taylor Available online 1980)
卷期:
Volume 22,
issue 1
页码: 49-53
ISSN:0040-1706
年代: 1980
DOI:10.1080/00401706.1980.10486100
出版商: Taylor & Francis Group
关键词: Regression;Subset selection;Multiple correlation coefficient;Stepwise regression;Monte Carlo
数据来源: Taylor
摘要:
When subset selection is used in regression the expected value ofR2is substantially inflated above its value without selection, especially when the number of observations is less than the number of predictor variables. The extent of this increase was investigated by a Monte Carlo simulation. Tables are given with average values and percentage points ofR2for the null case of independence between the response variable and the predictor variables. Approximation formulas are provided to supplement the coverage in the tables.
点击下载:
PDF (452KB)
返 回