摘要：
The instrumental variable method is widely used in the health and social sciences for identification and estimation of causal effects in the presence of potential unmeasured confounding. In order to improve efficiency, multiple instruments
are routinely used, leading to concerns about bias due to possible violation of the  instrumental variable assumptions.
To address this concern, we introduce a new class of  g-estimators that are guaranteed to remain consistent and asymptotically normal for
the causal effect of interest provided that  a set of at least $\gamma$ out of $K$ candidate instruments are valid, for
$\gamma\leq K$ set by the analyst {\it ex ante}, without necessarily knowing the identity of the valid and invalid IVs. We provide formal semiparametric efficiency theory supporting our results.
Both  simulation studies and  applications to the UK Biobank data demonstrate the superior empirical performance of our estimators compared to  competing methods.

个人简介：刘中华博士现任美国哥伦比亚比亚大学生物统计系助理教授。此前他在香港大学任助理教授。2015年他从哈佛大学生物统计系获得博士学位。