B1232
Title: Fighting noise with noise: Causal inference with many candidate instruments
Authors: Xinyi Zhang - Johns Hopkins University (United States) [presenting]
Linbo Wang - University of Toronto (Canada)
Stanislav Volgushev - University of Toronto (Canada)
Dehan Kong - University of Toronto (Canada)
Abstract: Instrumental variable methods provide useful tools for inferring causal effects in the presence of unmeasured confounding. To apply these methods with large-scale data sets, finding valid instruments from a possibly large candidate set is a major challenge. In practice, most candidate instruments are often irrelevant for studying a particular exposure of interest. Moreover, not all relevant candidate instruments are valid, as they may directly influence the outcome of interest. A data-driven method is proposed for causal inference with many candidate instruments that address these two challenges simultaneously. A key component of the proposal is a novel resampling method, which constructs pseudo-variables to remove irrelevant variables having spurious correlations with the exposure. Synthetic data analyses show that the proposed method performs favorably compared to existing methods. The method is applied to a Mendelian randomization study estimating the effect of obesity on health-related quality of life.
