Identification and Estimation of Local Average Treatment Effects

By Joshua D. Angrist, Guido W. Imbens. 1994

Subfields: Statistics and Probability, Causal Inference & Discovery

How researchers see this paper

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

In Statistics and Probability

In Causal Inference & Discovery

Citations in the corpus

Causal Regularization (2019, background): “Given observations from any further variables other than X and Y , conditional independences may help to detect or disprove the existence of common causes [5], and so-called instrumental variables may admit the identification of causal influence [6].”
The Econometrics of Randomized Experiments (2016, background): “…Cuzick, Edwards, and Segnan (1997), contain early and independent discussions of the instrumental variables approach, some in the special case of one-sided non-compliance, and Imbens and Angrist (1994), Angrist, Imbens and Rubin (1996) develop the general set up in the potential outcomes framework.”
Causal Inference Using Potential Outcomes (2005, background): “In any case, whatever name we wish to use for potential outcomes or for their use to define causal effects, they have rapidly become standard in many branches of social, economic, and biomedical sciences over the last two decades (e.g., Frangakis and Baker 2001; Gelman and King 1990; Heckman 1989; I”
Instrumental variables and the sign of the average treatment effect (2019, unknown): “Other related literature includes the local average treatment effect literature (LATE) (Imbens and Angrist, 1994) and the local instrumental variables/non-parametric selection model literature (Heckman and Vytlacil, 2001b), both of which impose monotonicity in the equation for the endogenous regress”
The effect of education on poverty: A European perspective (2021, background): “The identified effect is thus a local average treatment effect (LATE) (Imbens and Angrist, 1994).”
Causal Inference without Counterfactuals (2000, background): “A similar untestable assumption commonly made in the case of binary responses (Imbens and Angrist 1994) is monotonicity, which requires that P (Y, = 1, yt = 0) = 0 (where the response 1 represents a successful, and 0 an unsuccessful, outcome).”
A Critical Survey of Empirical Methods for Evaluating Active Labor Market Policies (2000, background): “Such sensitivity analyses would represent an improvement on much current partial equilibrium research that simply ignores general equilibrium effects.”