Asymptotic optimality of full cross-validation for selecting linear regression models

被引：8

作者：

Droge, B ^{[1
]}

机构：

[1] Humboldt Univ, Inst Math, D-10099 Berlin, Germany

来源：

STATISTICS & PROBABILITY LETTERS | 1999年 / 44卷 / 04期

关键词：

cross-validation; full cross-validation; model selection; prediction; asymptotic optimality;

D O I：

10.1016/S0167-7152(99)00026-7

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

For the problem of model selection, full cross-validation has been proposed as an alternative criterion to the traditional cross-validation, particularly in cases where the latter is not well defined. To justify the use of the new proposal we show that under some conditions, both criteria share the same asymptotic optimality property when selecting among linear regression models. (C) 1999 Elsevier Science B.V. All rights reserved.

引用

页码：351 / 357

页数：7

共 14 条

[1] BOOTSTRAP AND CROSS-VALIDATION ESTIMATES OF THE PREDICTION ERROR FOR LINEAR-REGRESSION MODELS [J].