Some approximations to the path formula for some nonlinear models

被引:0
|
作者
Kartsonaki, Christiana [1 ]
机构
[1] Univ Oxford, Nuffield Dept Populat Hlth, Oxford, England
关键词
mediation; path formula; regression; CAUSAL MEDIATION ANALYSIS; SURVIVAL;
D O I
10.1111/sjos.12753
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
In linear least squares regression there exists a simple decomposition of the effect of an exposure on an outcome into two parts in the presence of an intermediate variable. This decomposition is described and then analogous decompositions for other models are examined, namely for logistic regression and proportional hazards models.
引用
下载
收藏
页数:17
相关论文
共 50 条