Page 202 - 《社会》2022年第3期
P. 202
图形的逻辑力量:因果图的概念及其应用
图形的逻辑力量:因果图 社会
2022·3
CJS
的概念及其应用 第 42 卷
句国栋 陈云松
摘 要:本文旨在系统性地引介因果图方法,一种社会科学领域新近发展起来
的探究因果推断的非参数估计工具。 首先对因果图的基本概念和构型进行介
绍,讨论变量之间不同“通路”对应的开启和阻断规则及因果推断中的三种偏
差来源,即混淆偏差、过度控制偏差、内生性选择偏差。 在此基础上,本文将因
果图框架与现有定量社会科学研究中基于回归模型的因果推断方法思路进行
融合,结合实际案例使用因果图阐释包括遗漏变量、样本选择、自选择及联立
性在内的四种内生性问题,并对多元回归与匹配、代理变量、实验、工具变量、
面板模型等因果推断方法的运行机制进行了图形化。最后,本文使用因果图厘
清一些关于因果推断的不准确理解。
关键词:因果图 非参因果推断 混淆偏差 过度控制 内生性选择偏差
The Logical Power of Graphs:The Concept of Causal Graphs
and Their Applications
JU Guodong CHEN Yunsong
Abstract: Causal inference is a core problem in empirical research in the social
sciences,but understanding the context of causal inference relies on algebraic
derivation,a fact that hinders the prevalence of causal knowledge among sociologists.
Causal graphs derived from computer science can intuitively present casual paths and
control strategies in a graphical way,thereby providing people with a non鄄parametric
toolkit for understanding causal problems. This paper aims to provide a comprehensive
introduction to the causal graph method and integrate it with the existing framework of
causal inference based on regression models. This article first introduces the conceptual
rules and the three basic configurations of chain,fork,and inverted fork that make up
* 作者 1: 句国栋 伦敦政治经济学院社会政策系 (Author 1:JU Guodong,London School of
Economics and Political Science);作者 2:陈云松 南京大学社会学院(Author 2:CHEN Yunsong,
School of Social and Behavioral Sciences,Nanjing University)E-mail:yunsong.chen@nju.edu.cn
· 195·