Direct and Indirect Effects of Sequential Treatments

Abstract

In this paper we review the notion of direct causal effect as introduced by Pearl (2001). We show how it can be formulated without counterfactuals, using intervention indicators instead. This allows to consider the natural direct effect as a special case of sequential treatments discussed by Dawid and Didelez (2005) which immediately yields conditions for identifiability as well as a graphical way of checking identifiability. The results are contrasted with the criteria given by Pearl (2001) and Robins (2003).

Appears in Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence (UAI2006)

References in corpus (1)

• Probabilistic Evaluation of Sequential Plans from Causal Models with Hidden Variables

Cited by in corpus (18)

• Insights into the "cross-world" independence assumption of causal mediation analysis
• Identifying the consequences of dynamic treatment strategies: A decision-theoretic overview
• Graphical Models for Inference Under Outcome-Dependent Sampling
• Non-parametric efficient causal mediation with intermediate confounders
• Time-dependent mediators in survival analysis: Modelling direct and indirect effects with the additive hazards model
• Non-linear Mediation Analysis with High-dimensional Mediators whose Causal Structure is Unknown
• Causal Reasoning in Graphical Time Series Models
• Identifying Dynamic Sequential Plans
• Heterogeneous Indirect Effects for Multiple Mediators using Interventional Effect Models
• Robust and Flexible Estimation of Stochastic Mediation Effects: A Proposed Method and Example in a Randomized Trial Setting
• Causal mediation analysis: From simple to more robust strategies for estimation of marginal natural (in)direct effects
• Causal Mediation Analysis for Sparse and Irregular Longitudinal Data
• Decision-theoretic foundations for statistical causality
• Complier stochastic direct effects: identification and robust estimation
• An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization
• Causal organic indirect and direct effects: closer to Baron and Kenny, with a product method for binary mediators
• Graphical models for mediation analysis
• When the ends don't justify the means: Learning a treatment strategy to prevent harmful indirect effects