社会杂志

• 论文 • 上一篇    下一篇

社会学定量分析中的内生性问题——测估社会互动的因果效应研究综述

*作者:陈云松 牛津大学纽菲尔德学院(Author 1: Chen Yunsong, Nuffield College,Oxford University) Email: yunsong.chen@nuffield.ox.ac.uk;
作者2:范晓光,浙江省社会科学院社会学研究所(Author 2: Fan Xiaoguang, Institute of Sociology, Zhejiang Academy of Social Sciences)   

  1. *作者:陈云松 牛津大学纽菲尔德学院; 作者2:范晓光,浙江省社会科学院社会学研究所
  • 出版日期:2010-07-20 发布日期:2010-07-20
  • 通讯作者: *作者:陈云松 牛津大学纽菲尔德学院; E-mail:yunsong.chen@nuffield.ox.ac.uk;
  • 作者简介:*作者:陈云松 牛津大学纽菲尔德学院 作者2:范晓光,浙江省社会科学院社会学研究所

The Endogeneity Problem in Quantitative Analysis: A Review of Estimating Causal Effects of Social Interaction

*作者:陈云松 牛津大学纽菲尔德学院
作者2:范晓光,浙江省社会科学院社会学研究所   

  1. *Author 1: Chen Yunsong, Nuffield College,Oxford University;
    Author 2: Fan Xiaoguang, Institute of Sociology,Zhejiang Academy of Social Sciences.
  • Online:2010-07-20 Published:2010-07-20
  • Contact: Author 1: Chen Yunsong, Nuffield College,Oxford University; E-mail:yunsong.chen@nuffield.ox.ac.uk;
  • About author:*Author 1: Chen Yunsong, Nuffield College,Oxford University)E-mail: yunsong.chen@nuffield.ox.ac.uk; Author 2: Fan Xiaoguang, Institute of Sociology,Zhejiang Academy of Social Sciences.

摘要:

因果关系是社会学分析的核心议题。然而,基于调查数据的定量分析都会受到内生性问题的困扰,从而往

往难以作出恰当的因果性推断。大量现有的社会学定量分析虽以解释为己任,但实质上要么仅仅停留在描述统计相

关阶段,要么得出错误的因果性结论。本文以社会互动研究为例,详细讨论了遗漏偏误、自选择偏误、样本选择偏

误和联立性偏误等四种主要的内生性问题的来源,并介绍了克服内生性问题的一系列模型识别方法。最后还基于中

国综合调查(CGSS2003)问卷,提出了通过提高调查数据信息量以利克服内生性问题的可能性。

关键词: 内生性 ,  因果效应 ,  社会互动

Abstract:

 Causeeffect relationships are the core area in sociological analysis. However,

sociological analysis based on survey data is confronted by the endogeneity problem which plagues

causal inferences. Many existing studies aiming at providing explanations for social phenomena

either merely describes the statistical associations among variables or arrives at problematic

causal conclusions. Focusing on the social interaction studies, this paper addresses the major

sources of potential endogeneity biases, namely, the omitted variable bias, selfselection bias

, sampleselection bias and the simultaneity bias. Useful model identification strategies for

correcting these problems are reviewed. Based on CGSS2003, this paper also discusses how to

partially correct for the endogeneity problem through augmenting the volume of survey data.

Key words: endogeneity ,  causal effects ,  social interaction