Robust inference in summary data Mendelian randomization via the zero modal pleiotropy assumption

TLDR

Mendelian randomization is increasingly used to strengthen causal inference in observational studies, and recent summary‑data methods such as MR‑Egger and weighted median relax instrumental variable assumptions. The authors propose the mode‑based estimate (MBE) to obtain a single causal effect estimate from multiple genetic instruments and evaluate its performance in simulations and real data on lipid fractions, urate, and coronary heart disease. MBE uses summary data from large GWAS in a two‑sample design, estimating the causal effect as the mode of individual‑instrument estimates, which is consistent when the largest cluster of similar estimates comes from valid instruments. In simulations, MBE shows lower bias and type‑I error than other methods under the null, has moderate power—lower than IVW and weighted median but higher than MR‑Egger—and requires smaller sample sizes, making it a useful sensitivity analysis tool.

Abstract

Mendelian randomization (MR) is being increasingly used to strengthen causal inference in observational studies. Availability of summary data of genetic associations for a variety of phenotypes from large genome-wide association studies (GWAS) allows straightforward application of MR using summary data methods, typically in a two-sample design. In addition to the conventional inverse variance weighting (IVW) method, recently developed summary data MR methods, such as the MR-Egger and weighted median approaches, allow a relaxation of the instrumental variable assumptions.Here, a new method - the mode-based estimate (MBE) - is proposed to obtain a single causal effect estimate from multiple genetic instruments. The MBE is consistent when the largest number of similar (identical in infinite samples) individual-instrument causal effect estimates comes from valid instruments, even if the majority of instruments are invalid. We evaluate the performance of the method in simulations designed to mimic the two-sample summary data setting, and demonstrate its use by investigating the causal effect of plasma lipid fractions and urate levels on coronary heart disease risk.The MBE presented less bias and lower type-I error rates than other methods under the null in many situations. Its power to detect a causal effect was smaller compared with the IVW and weighted median methods, but was larger than that of MR-Egger regression, with sample size requirements typically smaller than those available from GWAS consortia.The MBE relaxes the instrumental variable assumptions, and should be used in combination with other approaches in sensitivity analyses.