Robust causal inference with continuous instruments using the local instrumental variable curve
Edward H. Kennedy, Scott A. Lorch, Dylan S. Small

TL;DR
This paper introduces a novel semiparametric doubly robust method for estimating the local instrumental variable effect curve with continuous instruments, addressing limitations of existing approaches and enabling flexible, robust causal inference.
Contribution
It develops the first doubly robust estimators for the local IV effect curve that are flexible, robust to misspecification, and incorporate instrument mechanism information.
Findings
Method applied to neonatal intensive care units, revealing effects of technical capacity on infant mortality.
Estimator demonstrates robustness to model misspecification and flexible effect modification estimation.
Asymptotic properties established under weak conditions.
Abstract
Instrumental variables are commonly used to estimate effects of a treatment afflicted by unmeasured confounding, and in practice instruments are often continuous (e.g., measures of distance, or treatment preference). However, available methods for continuous instruments have important limitations: they either require restrictive parametric assumptions for identification, or else rely on modeling both the outcome and treatment process well (and require modeling effect modification by all adjustment covariates). In this work we develop the first semiparametric doubly robust estimators of the local instrumental variable effect curve, i.e., the effect among those who would take treatment for instrument values above some threshold and not below. In addition to being robust to misspecification of either the instrument or treatment/outcome processes, our approach also incorporates information…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
