Efficient least squares for estimating total effects under linearity and causal sufficiency

Abstract

Recursive linear structural equation models are widely used to postulate causal mechanisms underlying observational data. In these models, each variable equals a linear combination of a subset of the remaining variables plus an error term. When there is no unobserved confounding or selection bias, the error terms are assumed to be independent. We consider estimating a total causal effect in this setting. The causal structure is assumed to be known only up to a maximally oriented partially directed acyclic graph (MPDAG), a general class of graphs that can represent a Markov equivalence class of directed acyclic graphs (DAGs) with added background knowledge. We propose a simple estimator based on recursive least squares, which can consistently estimate any identified total causal effect, under point or joint intervention. We show that this estimator is the most efficient among all regular estimators that are based on the sample covariance, which includes covariate adjustment and the estimators employed by the joint-IDA algorithm. Notably, our result holds without assuming Gaussian errors.

arXiv commentMinor edits

References in corpus (16)

• Causal Inference and Causal Explanation with Background Knowledge
• Estimating high-dimensional intervention effects from observational data
• Characterization and Greedy Learning of Interventional Markov Equivalence Classes of Directed Acyclic Graphs
• Identifiability of Gaussian structural equation models with equal error variances
• On the Validity of Covariate Adjustment for Estimating Causal Effects
• A generalized back-door criterion
• Global identifiability of linear structural equation models
• Graphical Criteria for Efficient Total Effect Estimation via Adjustment in Causal Linear Models
• Permutation-based Causal Inference Algorithms with Interventions
• Causal discovery of linear acyclic models with arbitrary distributions
• Computing maximum likelihood estimates in recursive linear models with correlated errors
• Maximum Likelihood Estimation in Gaussian Chain Graph Models under the Alternative Markov Property
• Interpreting and using CPDAGs with background knowledge
• Algebraic Problems in Structural Equation Modeling
• Efficient adjustment sets in causal graphical models with hidden variables
• Estimating Treatment Effects with Observed Confounders and Mediators

Cited by in corpus (3)

• On efficient adjustment in causal graphs
• Model selection for estimation of causal parameters
• Minimal enumeration of all possible total effects in a Markov equivalence class