A0738
Title: G-estimation with invalid instrumental variables
Authors: BaoLuo Sun - National University of Singapore (Singapore) [presenting]
Zhonghua Liu - Columbia University (United States)
Eric Tchetgen Tchetgen - The Wharton School, University of Pennsylvania (United States)
Abstract: The instrumental variable method is widely used in the health and social sciences to identify and estimate causal effects in the presence of potentially unmeasured confounding. Multiple instruments are routinely used to improve efficiency, leading to concerns about bias due to possible violation of the instrumental variable assumptions. To address this concern, a new class of g-estimators that are guaranteed is introduced to remain consistent and asymptotically normal for the causal effect of interest provided that a set of at least $k$ out of $K$ candidate instruments are valid, for some value of $k$ set by the analyst ex-ante, without necessarily knowing the identities of the valid and invalid instruments.
