Counterfactuals and Policy Analysis in Structural Models

By Alexander Balke, Judea Pearl. 1995

Evaluation of counterfactual queries (e.g., "If A were true, would C have been true?") is important to fault diagnosis, planning, determination of liability, and policy analysis. We present a method for evaluating counterfactuals when the underlying causal model is represented by structural models - a nonlinear generalization of the simultaneous equations models commonly used in econometrics and social sciences. This new method provides a coherent means for evaluating policies involving the control of variables which, prior to enacting the policy were influenced by other variables in the system.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Causal inference in statistics: An overview (2009, background): “Realizing that units in this example fall into 16 equivalent classes, each representing a binary function X = f(z) paired with a binary function y = g(x), Balke and Pearl (1997) were able to derive closed-form solutions for these bounds.”
Probabilities Of Causation: Three Counterfactual Interpretations And Their Identification (1999, background): “…is that the latter enjoys natural and formal semantics in terms of structural models (Galles and Pearl 1997, 1998; Halpern 1998; Pearl 2000), as well as effective procedures for computing probabilities of counterfactual expressions from a given causal theory (Balke and Pearl 1994a, 1995).”
Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes (2019, background): “5 exploit the sequential functional relationships among states and treatments in the underlying DTR, which improve over the best-known bounds reported in [17, 3, 39].”
TRYGVE HAAVELMO AND THE EMERGENCE OF CAUSAL CALCULUS (2014, unknown): “…al., 1993).7 This operation, called do-operator, has subsequently led to do-calculus (Pearl, 1994, 2000) and to the structural theory of counterfactuals (Balke and Pearl, 1995; Pearl, 2000, Ch. 7), which unifies structural equation modeling with the potential outcome paradigm of Neyman (1923) and…”
Instrumental Variables: An Econometrician's Perspective (2014, unknown): “…include Robins (1989), Heckman (1990), Manski (1990), Imbens and Angrist (1994), Angrist, Imbens and Rubin (1996), Robins and Greenland (1996), Balke and Pearl (1995, 1997), Greenland (2000), Hernán and Robins (2006), Robins (1994), Robins and Rotnitzky (2004), Vansteelandt and Goetghebeur…”
3. The Foundations of Causal Inference (2010, methodology): “These were later generalized by Balke and Pearl (1995), using surgeries (equation 29), thus permitting endogenous variables to serve as counterfactual antecedents. The “surgery definition” was used in Pearl (2000a, p. 417) and criticized by Cartwright (2007) and Heckman (2005); see Pearl (2009a:362–”
Statistics and causal inference: A review (2003, methodology): “Moreover, it can be shown that, in the absence of additional assumptions, the treatment effect in such graphs cannot be identified by any method whatsoever Balke and Pearl (1997); one must therefore resort to approximate methods of assessment.”
Interpretation and identification of causal mediation. (2014, unknown): “…1988; Rubin, 1974) and epidemiology (Robins and Greenland, 1992), together with a formal semantics based on non-parametric structural equations (Balke and Pearl, 1995; Halpern, 1998; Pearl, 2001) have given causal mediation analysis a sound theoretical basis and have extended its scope from…”
The Causal Foundations of Structural Equation Modeling (2012, methodology): “These were later generalized by Balke and Pearl (1995), using surgeries (equation 6), thus permitting endogenous variables to serve as counterfactual antecedents.”
Causal and Counterfactual Inference (2018, background): “(3) was first introduced in Balke & Pearl (1995).”