No retraction, correction or concern found when last checked on Nov 1, 2026.

The use of two-sample methods for Mendelian randomization analyses on single large datasets

Cosetta Minelli, Fabiola Del Greco M., Diana A van der Plaat and 3 more

International Journal of Epidemiology · 2021 · CC BY

doi:10.1101/2020.05.07.082206

Abstract

Background. With genome-wide association data for many exposures and outcomes now available from large biobanks, one-sample Mendelian randomization (MR) is increasingly used to investigate causal relationships. Many robust MR methods are available to address pleiotropy, but these assume independence between the gene-exposure and gene-outcome association estimates. Unlike in two-sample MR, in one-sample MR the two estimates are obtained from the same individuals, and the assumption of independence does not hold in the presence of confounding.

Methods. With simulations mimicking a typical study in UK Biobank, we assessed the performance, in terms of bias and precision of the MR estimate, of the fixed-effect and (multiplicative) random-effects meta-analysis method, weighted median estimator, weighted mode estimator and MR-Egger regression, used in both one-sample and two-sample data. We considered scenarios differing by the: presence/absence of a true causal effect; amount of confounding; and presence and type of pleiotropy (none, balanced or directional).

Results. Even in the presence of substantial correlation due to confounding, all two-sample methods used in one-sample MR performed similarly to when used in two-sample MR, except for MR-Egger which resulted in bias reflecting direction and magnitude of the confounding. Such bias was much reduced in the presence of very high variability in instrument strength across variants (IGX2 of 97%).

Conclusions. Two-sample MR methods can be safely used for one-sample MR performed within large biobanks, expect for MR-Egger. MR-Egger is not recommended for one-sample MR unless the correlation between the gene-exposure and gene-outcome estimates due to confounding can be kept low, or the variability in instrument strength is very high.

References 22

1.
Davey Smith G, Ebrahim S. ‘Mendelian randomization’: can genetic epidemiology contribute to understanding environmental determinants of disease? Int J Epidemiol 2003;32:1–22.
Not in our library10.1093/ije/dyg070
2.
Didelez V, Sheehan N. Mendelian randomization as an instrumental variable approach to causal inference. Stat Methods Med Res2007;16:309–30.
Not in our library10.1177/0962280206077743
3.
A review of instrumental variable estimators for Mendelian randomization · 2015
No notice
4.
Mendelian Randomization Analysis With Multiple Genetic Variants Using Summarized Data · 2013
No notice
5.
Thompson JR, Minelli C, Del GM. Mendelian randomization using public data from genetic consortia. Int J Biostat2016;12. pii: /j/ijb.2016..
Not in our library10.1515/ijb-2015-0074
6.
Pierce BL, Ahsan H, Vanderweele TJ. Power and instrument strength requirements for Mendelian randomization studies using multiple genetic variants. Int J Epidemiol2011;40:740–52.
Not in our library10.1093/ije/dyq151
7.
Zhao Q, Wang J, Spiller W, Bowden J, Small DS. Two-sample instrumental variable analyses using heterogeneous samples. Stat Sci2019;34:317–33.
Not in our library
8.
Bycroft C, Freeman C, Petkova D et al Genome-wide genetic data on ∼500,000 UK Biobank participants. bioRxiv2017, 20 July. 166298.
Not in our library
9.
Evaluating the potential role of pleiotropy in Mendelian randomization studies · 2018
No notice
10.
Bias due to participant overlap in two‐sample Mendelian randomization · 2016
No notice
11.
Burgess S, Thompson SG; CRP CHD Genetics Collaboration. Avoiding bias from weak instruments in Mendelian randomization studies. Int J Epidemiol2011;40:755–64.
Not in our library10.1093/ije/dyr036
12.
Assessing the suitability of summary data for two-sample Mendelian randomization analyses using MR-Egger regression: the role of the I2 statistic · 2016
No notice
13.
Minelli C, van der Plaat DA, Leynaert B et al Age at puberty and risk of asthma: a Mendelian randomisation study. PLoS Med2018;15:e1002634.
Not in our library10.1371/journal.pmed.1002634
14.
Lawlor DA, Harbord RM, Sterne JA, Timpson N, Davey Smith G. Mendelian randomization: using genes as instruments for making causal inferences in epidemiology. Stat Med2008;27:1133–63.
Not in our library10.1002/sim.3034
15.
Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression · 2015
No notice
16.
A framework for the investigation of pleiotropy in two‐sample summary data Mendelian randomization · 2017
No notice
17.
Consistent Estimation in Mendelian Randomization with Some Invalid Instruments Using a Weighted Median Estimator · 2016
No notice
18.
Robust inference in summary data Mendelian randomization via the zero modal pleiotropy assumption · 2017
No notice
19.
Combining information on multiple instrumental variables in Mendelian randomization: comparison of allele score and summarized data methods · 2015
No notice
20.
Bowden J, Burgess S, Davey Smith G. Response to Hartwig and Davies. Int J Epidemiol2016;45:1679–80.
Not in our library10.1093/ije/dyw252
21.
Hartwig FP, Davies NM. Why internal weights should be avoided (not only) in MR-Egger regression. Int J Epidemiol2016;45:1676–78.
Not in our library10.1093/ije/dyw240
22.
Burgess S, Davey SG, Davies NM et al Guidelines for performing Mendelian randomization investigations. Wellcome Open Res2019;4:186.
Not in our library10.12688/wellcomeopenres.15555.1

Cited by papers we hold 3

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.