EconBase
← All papers

Deep Generalized Method of Moments for Instrumental Variable Analysis

Andrew Bennett, Nathan Kallus, Tobias Schnabel

arXiv 29 May 2019 · Statistics — Machine Learning · 31 citations (OpenAlex)

arXiv:1905.12495 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Instrumental variable analysis is a powerful tool for estimating causal effects when randomization or full control of confounders is not possible. The application of standard methods such as 2SLS, GMM, and more recent variants are significantly impeded when the causal effects are complex, the instruments are high-dimensional, and/or the treatment is high-dimensional. In this paper, we propose the DeepGMM algorithm to overcome this. Our algorithm is based on a new variational reformulation of GMM with optimal inverse-covariance weighting that allows us to efficiently control very many moment conditions. We further develop practical techniques for optimization and model selection that make it particularly successful in practice. Our algorithm is also computationally tractable and can handle large-scale datasets. Numerical results show our algorithm matches the performance of the best tuned methods in standard settings and continues to work in high-dimensional settings where even recent methods break.

Citation extraction

34
references
47
in-text mentions
34
distinct cited
0
self-citations
6,449
main-text words

appendix boundary found by appendix_command · 63% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1G. Lewis and V. Syrgkanis (2018) Adversarial generalized method of moments1.00064100%
2J. Hartford, G. Lewis, K. Leyton-Brown, and M. Taddy (2017) Deep iv: A flexible approach for counterfactual prediction0.84333100%
3J. D. Angrist and J.-S. Pischke (2008) Mostly Harmless Econometrics: An Empiricist's Companion0.73732100%
4C. Daskalakis, A. Ilyas, V. Syrgkanis, and H. Zeng (2017) Training gans with optimism0.64422100%
5L. P. Hansen (1982) Large sample properties of generalized method of moments estimators0.64422100%
6L. P. Hansen, J. Heaton, and A. Yaron (1996) Finite-sample properties of some alternative gmm estimators0.64422100%
7J. A. Cole, H. Norman, L. B. Weatherby, and A. M. Walker (2006) Drug copayment and adherence in chronic heart failure: effect on cost and outcomes0.51121100%
8C. Ai and X. Chen (2003) Efficient estimation of models with conditional moment restrictions containing unknown functions0.40511100%
9J. D. Angrist and A. B. Krueger (2001) Instrumental variables and the search for identification: From supply and demand to natural experiments0.40511100%
10M. Arjovsky, S. Chintala, and L. Bottou (2017) Wasserstein gan0.40511100%

Showing the top 10 of 34 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Dual Instrumental Variable Regression0.92843
2Efficient Policy Learning from Surrogate-Loss Classification Reductions0.87472
3Learning Causal Models from Conditional Moment Restrictions by Importance Weighting0.73733
4Machine learning the first stage in 2SLS: Practical guidance from bias decomposition and simulation0.73733
5Minimax Estimation of Conditional Moment Models0.727265
6Penalized GMM Framework for Inference on Functionals of Nonparametric Instrumental Variable Estimators0.64422
7Minimax Kernel Machine Learning for a Class of Doubly Robust Functionals with Application to Proximal Causal Inference0.55061
8Adversarial Estimators0.51121
9Minimax Instrumental Variable Regression and $L_2$ Convergence Guarantees without Identification or Closedness0.51121
10Conformal Prediction for Nonparametric Instrumental Regression0.51122