On the semi-parametric efficiency of logistic regression under case-control sampling

被引：42

作者：

Breslow, NE ^{[1
]}

Robins, JM

Wellner, JA

机构：

[1] Univ Washington, Dept Biostat, Seattle, WA 98195 USA

[2] Harvard Univ, Sch Publ Hlth, Dept Epidemiol, Boston, MA 02115 USA

[3] Univ Washington, Dept Stat, Seattle, WA 98195 USA

来源：

BERNOULLI | 2000年 / 6卷 / 03期

关键词：

biased sampling; epidemiology; influence function;

D O I：

10.2307/3318670

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：

Using modern theory for semi-parametric models, we provide details for an argument of Robins et al. showing efficiency of the standard logistic regression estimator applied to data from case-control studies. Our elaboration of this argument, and of a related one by Bickel et al., includes a constructive new proof of the result.

引用

页码：447 / 455

页数：9

共 14 条

[1] COX REGRESSION-MODEL FOR COUNTING-PROCESSES - A LARGE SAMPLE STUDY [J].