Journal of Economic Perspectives—Volume 15, Number 4—Fall 2001—Pages 69–85 Instrumental Variables and the Search for Identification: From Supply and Demand to Natural Experiments

2,660 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Education, Statistics and Probability

How researchers see this paper

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

In Economics and Econometrics

In Education

In Statistics and Probability

Citations in the corpus

Avoiding Discrimination through Causal Reasoning (2017, background): “Estimating direct causal effects is a hard problem, well studied by the causality community and often involves instrumental variables [23].”
Interventional Few-Shot Learning (2020, background): “Therefore, as we formally show in Appendix 1, the key causal difference between MSL and FSL is: MSL essentially makes I an instrumental variable [1] that achieves P (Y |X) := P (Y |I) ≈ P (Y |do(X)).”
Statistical Models for Causation (2006, background): “There is a useful survey by Angrist and Krueger (2001). Robins (1999) demonstrates the essential ambiguity in regression-type adjustments for confounders; also see Scharfstein, Rotnitzky and Robins (1999). Heckman (2000) considers the role of potential responses in economics, and the limitations of ”
Identification and Inference for Econometric Models: On Specifying Graphical Models for Causation and the Identification Problem (2005, neutral): “Angrist and Krueger (2001) provide a nice introduction to instrumental variables; an early application of the technique was to fit supply and demand curves for butter (Wright, 1928, p.316).”
Financial literacy, financial advice, and financial behavior (2017, background): “Observational studies using carefully chosen IVs are sometimes regarded as being equivalent to quasi experiments regarding their power to support causal claims (Angrist and Krueger 2001).”
Broadband Infrastructure and Economic Growth (2011, methodology): “Using a non-linear first stage to generate fitted values that are subsequently used in the second-stage equation is not innocuous because it generates consistent estimates only if the non-linear first-stage model is correctly specified (Angrist and Krueger 2001).”
The Determinants of Happiness of China’s Elderly Population (2012, background): “Angrist and Krueger (2001) state that, even if the underlying second-stage relationship is nonlinear, linear instrumental variables estimates typically capture an average effect of economic interest analogous to the LATE parameter for dummy endogenous regressors.”
What’s in a p? Reassessing best practices for conducting and reporting hypothesis-testing research (2017, methodology): “Probably the best-known technical solutions are lagged explanatory variables and the instrumental variables method (Angrist & Krueger, 2001).”