An examination of multivariable Mendelian randomization in the single-sample and two-sample summary data settings

By E. Sanderson, George Davey Smith, F. Windmeijer, J. Bowden. bioRxiv, 2018

972 citations recorded by the source corpus.

Background Mendelian Randomisation (MR) is a powerful tool in epidemiology which can be used to estimate the causal effect of an exposure on an outcome in the presence of unobserved confounding, by utilising genetic variants that are instrumental variables (IVs) for the exposure. This has been extended to Multivariable MR (MVMR) to estimate the effect of two or more exposures on an outcome. Methods/Results We use simulations and theory to clarify the interpretation of estimated effects in a MVMR analysis under a range of underlying scenarios, where a secondary exposure acts variously as a confounder, a mediator, a pleiotropic pathway and a collider. We then describe how instrument strength and validity can be assessed for an MVMR analysis in the single sample setting, and develop tests to assess these assumptions in the popular two-sample summary data setting. We illustrate our methods using data from UK biobank to estimate the effect of education and cognitive ability on body mass index. Conclusion MVMR analysis consistently estimates the effect of an exposure, or exposures, of interest and provides a powerful tool for determining causal effects in a wide range of scenarios with either individual or summary level data.

Subfields: Genetics, Rheumatology, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/54974fa51e079c130ac045a669aa7a7b0db0d942

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Genetics

1. E. Sanderson
2. J. Bowden
3. George Davey Smith
4. Michael Holmes
5. F. Hartwig
6. F. Windmeijer
7. T. Palmer
8. Mika Ala-Korpela

In Rheumatology

1. E. Sanderson
2. J. Bowden
3. F. Hartwig
4. Michael Holmes
5. Mika Ala-Korpela
6. T. Palmer
7. F. Windmeijer
8. George Davey Smith

In Statistics and Probability

1. E. Sanderson
2. Michael Holmes
3. George Davey Smith
4. J. Bowden
5. F. Hartwig
6. F. Windmeijer
7. Mika Ala-Korpela
8. T. Palmer

Citations in the corpus

• Multivariable Mendelian Randomization and Mediation. (2020, methodology): “This has recently been extended to estimate the independent direct effects of multiple, potentially related, exposures through multivariable MR (MVMR) (Burgess and Thompson 2015; Sanderson et al. 2019).”
• The confidence interval method for selecting valid instrumental variables (2019, methodology): “Recent analyses have considered models with multiple treatments, see for example Sanderson et al. (2019) for an examination of multivariable Mendelian randomisation.”
• Evaluating the relationship between circulating lipoprotein lipids and apolipoproteins with risk of coronary heart disease: A multivariable Mendelian randomisation analysis (2020, methodology): “, an effect that is not mediated by any other factor in the model [28]); see S1 Fig for further details.”