Identification of Causal effects Using Instrumental Variables

By Guido W. Imbens, Joshua D. Angrist, Donald B. Rubin. 1996

How researchers see this paper

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

In Causal Inference & Discovery

Citations in the corpus

Invariant Causal Prediction for Nonlinear Models (2017, background): “The assumption of no direct eﬀect of E on Y is analogous to the typical assumptions about instrumental variables (Angrist et al., 1996; Imbens, 2014).”
Causal inference by using invariant prediction: identification and confidence intervals (2015, methodology): “We can use I as an instrument in a classical sense and estimate γ∗ by the following well-known two-stage least squares procedure [Angrist et al., 1996]: first we estimate the influence of I on X and then we regress Y on the predicted values of X given I.”
Counterfactual Prediction with Deep Instrumental Variables Networks (2016, methodology): “Most IV applications make use of a two-stage least squares procedure [2SLS; e.g., Angrist et al., 1996] that requires assumptions of linearity and homogeneity (e.g., all airline customers must have the same price sensitivity).”
Causal inference in statistics: An overview (2009, background): “On the other hand, the algebraic machinery offered by the counterfactual notation, Yx(u), once a problem is properly formalized, can be extremely powerful in refining assumptions (Angrist et al., 1996; Heckman and Vytlacil, 2005), deriving consistent estimands (Robins, 1986), bounding probabilities ”
Causal Structure Learning (2017, background): “Shift interventions are standard in the econometric literature on instrumental variables with binary treatments where the additive shift of an exogenous instrument changes the probability of a binary treatment variable (Angrist et al., 1996).”
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, background): “Future research in this direction may explore less strict settings, perhaps accounting for hidden confounders, or partially observed graphs [9, 44, 168], further adding to the uncertainy of recourse recommendations.”
Principal Stratification in Causal Inference (2002, unknown): “Considerable growth of literature has followed or was proposed independently of Imbens and Rubin (1994, 1997 ) on methods to better address noncompliance (e.g., Baker and Lindeman , 1994; Robins and Greenland, 1994; Angrist et al., 1996, Goetghebeur and Molenberghs, 1996; Robins, 1998; Rubin, 1998).”
Fertility and Female Labor Supply in Latin America: New Causal Evidence (2007, unknown): “…general, the Same sex IV strategy identifies the average effect of having more than two children on those whose fertility decisions are changed by the instrument (compliers), while OLS is suspected to fail at identifying the same effect averaged over the whole population (see Angrist et al, 1996).”
Regression-adjusted average treatment effect estimates in stratified randomized experiments (2019, background): “It would be interesting to extend the results to more complicated settings, such as covariates adjustment for multiple value treatment [11], for binary outcomes using logistic regression [12, 24, 35], and covariate adjustment in experiments when there is noncompliance [2, 3, 17].”
An Experimental Evaluation of a Comprehensive Employment-Oriented Prisoner Re-entry Program (2014, unknown): “In principle we could use random assignment to treatment as an instrumental variable to estimate the effects of program participation, which would reﬂect the effects of treatment on the treated if no Cs could access program services but in our application would instead be a local average treatment e”
Causal Dantzig: Fast inference in linear structural equation models with hidden variables under additive interventions (2017, background): “If an instrumental variable is available, then diﬀerent forms of instrumental variable regression [Wright, 1928, Bowden and Turkington, 1990, Angrist et al., 1996, Didelez et al., 2010] can be used to infer the causal eﬀect of a single variable on a target of interest.”
Do Women Pay More for Credit? Evidence from Italy (2008, unknown): “As a further robustness check, column (3) contains the same specifications as (1), estimated by means of panel techniques.”
Estimating Marginal Treatment Effects in Heterogeneous Populations (2008, methodology): “This heterogeneity was reformulated as a random coefficient by Heckman and Robb (1985) and by Björklund and Moffitt (1987). The latter paper also introduced the concept of the marginal treatment effect (termed the ‘marginal gain’) in the context of a multivariate-normal switching regression model an”