Total, Direct, and Indirect Effects in Logit and Probit Models

2013/05/01 by Richard Breen, Kristian Bernt Karlson, Anders Holm · 12 citations
Mathematics · Social Sciences · #Advanced Causal Inference Techniques #School Choice and Performance #Urban, Neighborhood, and Segregation Studies

paper · doi:10.1177/0049124113494572

Abstract

This article presents a method for estimating and interpreting total, direct, and indirect effects in logit or probit models. The method extends the decomposition properties of linear models to these models; it closes the much-discussed gap between results based on the “difference in coefficients” method and the “product of coefficients” method in mediation analysis involving nonlinear probability models models; it reports effects measured on both the logit or probit scale and the probability scale; and it identifies causal mediation effects under the sequential ignorability assumption. We also show that while our method is computationally simpler than other methods, it always performs as well as, or better than, these methods. Further derivations suggest a hitherto unrecognized issue in identifying heterogeneous mediation effects in nonlinear probability models. We conclude the article with an application of our method to data from the National Educational Longitudinal Study of 1988.

Citations

• Comparing Logit and Probit Coefficients Across Groups
• Regression Models with Ordinal Variables
• Estimating causal effects of treatments in randomized and nonrandomized studies.

Cited by

• The Long Arm of Conflict: How Timing Shapes the Impact of Childhood Exposure to War
• Employment stability and social origin: Cumulative advantages in young adults’ homeownership and financial asset accumulation
• Sorted and Tracked: English Learners, College-Level Course-Taking in High School, and Postsecondary Opportunity
• Gestational hypertension and childhood atopy: a Millennium Cohort Study analysis
• Marginal Odds Ratios: What They Are, How to Compute Them, and Why Sociologists Might Want to Use Them
• Interpreting and Understanding Logits, Probits, and Other Nonlinear Probability Models
• Virtual Socializing, Peers, and Juvenile Delinquency: A Study of Incarcerated Male Youths in China
• Causal Machine Learning: A Deductive–Inductive Framework for Sociological Research
• Politicians' high‐status signals make less‐educated citizens more supportive of aggression against government: A video‐vignette survey experiment
• Categorical Distinctions and Claims-Making: Opportunity, Agency, and Returns from Wage Negotiations
• Uncertainty Sets for Distributionally Robust Bandits Using Structural Equation Models
• The News You Choose: news media preferences amplify views on climate change

Related

• Interpreting and Understanding Logits, Probits, and Other Nonlinear Probability Models
• Quantifying and Testing Indirect Effects in Simple Mediation Models When the Constituent Paths Are Nonlinear
• Path Analysis for Binary Random Variables
• Random effects probit and logit: understanding predictions and marginal effects
• Bounds on direct and indirect effects under treatment/mediator endogeneity and outcome attrition