Causal Inference

Graphoids over Counterfactuals

September, 2014

Abstract

Augmenting the graphoid axioms with three additional rules enables us to handle independencies among observed as well as counterfactual variables. The augmented set of axioms facilitates the derivation of testable implications and ignorability conditions whenever modeling assumptions are articulated in the language of counterfactuals.

Graphical Tools for Linear Structural Equation Modeling

July, 2015

Abstract

This paper surveys graphical tools developed in the past three decades that are applicable to linear structural equation models (SEMs). These tools permit researchers to answer key research questions by simple path-tracing rules, even for highly complex models. They include parameter identification, causal effect identification, regressor selection, selecting instrumental variables, finding testable implications of a given model, identifying equivalent models and estimating counterfactual relationships.

Pages