EconBase
← All papers

Valid Causal Inference with (Some) Invalid Instruments

Jason Hartford, Victor Veitch, Dhanya Sridhar, Kevin Leyton-Brown

arXiv 19 Jun 2020 · Statistics — Methodology · 6 citations (OpenAlex)

arXiv:2006.11386 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Instrumental variable methods provide a powerful approach to estimating causal effects in the presence of unobserved confounding. But a key challenge when applying them is the reliance on untestable "exclusion" assumptions that rule out any relationship between the instrument variable and the response that is not mediated by the treatment. In this paper, we show how to perform consistent IV estimation despite violations of the exclusion assumption. In particular, we show that when one has multiple candidate instruments, only a majority of these candidates---or, more generally, the modal candidate-response relationship---needs to be valid to estimate the causal effect. Our approach uses an estimate of the modal prediction from an ensemble of instrumental variable estimators. The technique is simple to apply and is "black-box" in the sense that it may be used with any instrumental variable estimator as long as the treatment effect is identified for each valid instrument independently. As such, it is compatible with recent machine-learning based estimators that allow for the estimation of conditional average treatment effects (CATE) on complex, high dimensional data. Experimentally, we achieve accurate estimates of conditional average treatment effects using an ensemble of deep network-based estimators, including on a challenging simulated Mendelian Randomization problem.

Citation extraction

29
references
54
in-text mentions
29
distinct cited
0
self-citations
5,752
main-text words

appendix boundary found by appendix_command · 73% 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
1J. Hartford, G. Lewis, K. Leyton-Brown, and M. Taddy (2017) Deep IV: A flexible approach for counterfactual prediction0.88810470%
2W. K. Newey and J. L. Powell (2003) Instrumental variable estimation of nonparametric models0.73732100%
3F. P. Hartwig, G. Davey Smith, and J. Bowden (2017) Robust inference in summary data Mendelian randomization via the zero modal pleiotropy assumption0.7218338%
4R. Singh, M. Sahani, and A. Gretton (1906) Kernel instrumental variable regression0.64422100%
5A. Bennett, N. Kallus, and T. Schnabel (1905) Deep generalized method of moments for instrumental variable analysis0.64422100%
6S. Darolles, Y. Fan, J.-P. Florens, and E. Renault (2011) Nonparametric instrumental regression0.64422100%
7G. Hemani, J. Bowden, and G. Davey Smith (2018) Evaluating the potential role of pleiotropy in Mendelian randomization studies0.64422100%
8G. Lewis and V. Syrgkanis (2018) Adversarial generalized method of moments0.64422100%
9T. Dalenius (1965) The Mode–A Neglected Statistical Parameter0.51121100%
10J. H. Venter (1967) On Estimation of the Mode0.51121100%

Showing the top 10 of 29 scored citations.