Consistent Estimation in Mendelian Randomization with Some Invalid Instruments Using a Weighted Median Estimator
- PMID: 27061298
- PMCID: PMC4849733
- DOI: 10.1002/gepi.21965
Consistent Estimation in Mendelian Randomization with Some Invalid Instruments Using a Weighted Median Estimator
Abstract
Developments in genome-wide association studies and the increasing availability of summary genetic association data have made application of Mendelian randomization relatively straightforward. However, obtaining reliable results from a Mendelian randomization investigation remains problematic, as the conventional inverse-variance weighted method only gives consistent estimates if all of the genetic variants in the analysis are valid instrumental variables. We present a novel weighted median estimator for combining data on multiple genetic variants into a single causal estimate. This estimator is consistent even when up to 50% of the information comes from invalid instrumental variables. In a simulation analysis, it is shown to have better finite-sample Type 1 error rates than the inverse-variance weighted method, and is complementary to the recently proposed MR-Egger (Mendelian randomization-Egger) regression method. In analyses of the causal effects of low-density lipoprotein cholesterol and high-density lipoprotein cholesterol on coronary artery disease risk, the inverse-variance weighted method suggests a causal effect of both lipid fractions, whereas the weighted median and MR-Egger regression methods suggest a null effect of high-density lipoprotein cholesterol that corresponds with the experimental evidence. Both median-based and MR-Egger regression methods should be considered as sensitivity analyses for Mendelian randomization investigations with multiple genetic variants.
Keywords: Egger regression; Mendelian randomization; instrumental variables; pleiotropy; robust statistics.
© 2016 The Authors. *Genetic Epidemiology Published by Wiley Periodicals, Inc.
Figures
![Figure 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/4849733/bin/GEPI-40-304-g001.gif)
![Figure 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/4849733/bin/GEPI-40-304-g002.gif)
![Figure 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/4849733/bin/GEPI-40-304-g003.gif)
![Figure 4](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/4849733/bin/GEPI-40-304-g004.gif)
Similar articles
-
Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression.Int J Epidemiol. 2015 Apr;44(2):512-25. doi: 10.1093/ije/dyv080. Epub 2015 Jun 6. Int J Epidemiol. 2015. PMID: 26050253 Free PMC article.
-
Assessing the suitability of summary data for two-sample Mendelian randomization analyses using MR-Egger regression: the role of the I2 statistic.Int J Epidemiol. 2016 Dec 1;45(6):1961-1974. doi: 10.1093/ije/dyw220. Int J Epidemiol. 2016. PMID: 27616674 Free PMC article.
-
Extending the MR-Egger method for multivariable Mendelian randomization to correct for both measured and unmeasured pleiotropy.Stat Med. 2017 Dec 20;36(29):4705-4718. doi: 10.1002/sim.7492. Epub 2017 Sep 27. Stat Med. 2017. PMID: 28960498 Free PMC article.
-
Mendelian randomization to assess causal effects of blood lipids on coronary heart disease: lessons from the past and applications to the future.Curr Opin Endocrinol Diabetes Obes. 2016 Apr;23(2):124-30. doi: 10.1097/MED.0000000000000230. Curr Opin Endocrinol Diabetes Obes. 2016. PMID: 26910273 Free PMC article. Review.
-
Genetic Association of Lipids and Lipid Drug Targets With Abdominal Aortic Aneurysm: A Meta-analysis.JAMA Cardiol. 2018 Jan 1;3(1):26-33. doi: 10.1001/jamacardio.2017.4293. JAMA Cardiol. 2018. PMID: 29188294 Free PMC article. Review.
Cited by
-
Peripheral Immune Cells Contribute to the Pathogenesis of Alzheimer's Disease.Mol Neurobiol. 2024 Jun 6. doi: 10.1007/s12035-024-04266-6. Online ahead of print. Mol Neurobiol. 2024. PMID: 38842674
-
Association between inflammatory factors and melanoma: a bidirectional Mendelian randomization study.Cancer Causes Control. 2024 Jun 6. doi: 10.1007/s10552-024-01890-4. Online ahead of print. Cancer Causes Control. 2024. PMID: 38842646
-
Whole exome sequencing analyses reveal novel genes in telomere length and their biomedical implications.Geroscience. 2024 Jun 5. doi: 10.1007/s11357-024-01203-2. Online ahead of print. Geroscience. 2024. PMID: 38837026
-
The impact of cannabis use on erectile dysfunction and sex hormones: a Mendelian randomization analysis.Int J Impot Res. 2024 Jun 4. doi: 10.1038/s41443-024-00925-3. Online ahead of print. Int J Impot Res. 2024. PMID: 38834872
-
Investigating the causal relationship between thyroid dysfunction diseases and osteoporosis: a two-sample Mendelian randomization analysis.Sci Rep. 2024 Jun 4;14(1):12784. doi: 10.1038/s41598-024-62854-x. Sci Rep. 2024. PMID: 38834708 Free PMC article.
References
-
- Bochud M, Chiolero A, Elston R, Paccaud F. 2008. A cautionary note on the use of Mendelian randomization to infer causation in observational epidemiology. Int J Epidemiol 37(2):414–416. - PubMed
-
- Bowden J, Thompson J, Burton P. 2006. Using pseudo‐data to correct for publication bias in meta‐analysis. Stat Med 25: 3798–3813. - PubMed
-
- Burgess S, Thompson SG. 2015. Mendelian Randomization: Methods for Using Genetic Variants in Causal Estimation. Chapman & Hall, Boca Raton, FL, USA.
-
- Burgess S, Thompson S, CRP CHD Genetics Collaboration . 2011. Avoiding bias from weak instruments in Mendelian randomization studies. Int J Epidemiol 40(3):755–764. - PubMed
Publication types
MeSH terms
Substances
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources