Avoiding bias from weak instruments in Mendelian randomization studies
The DOI matches its Crossref record; 38 of the 40 references it cites were found in a registry or an index.
Abstract
BACKGROUND: Mendelian randomization is used to test and estimate the magnitude of a causal effect of a phenotype on an outcome by using genetic variants as instrumental variables (IVs). Estimates of association from IV analysis are biased in the direction of the confounded, observational association between phenotype and outcome. The magnitude of the bias depends on the F-statistic for the strength of relationship between IVs and phenotype. We seek to develop guidelines for the design and analysis of Mendelian randomization studies to minimize bias. METHODS: IV analysis was performed on simulated and real data to investigate the effect on bias of size of study, number and choice of instruments and method of analysis. RESULTS: Bias is shown to increase as the expected F-statistic decreases, and can be reduced by using parsimonious models of genetic association (i.e. not over-parameterized) and by adjusting for measured covariates. Using data from a single study, the causal estimate of a unit increase in log-transformed C-reactive protein on fibrinogen (μmol/l) is shown to increase from -0.005 (P = 0.99) to 0.792 (P = 0.00003) due to injudicious choice of instrument. Moreover, when the observed F-statistic is larger than expected in a particular study, the causal estimate is more biased towards the observational association and its standard error is smaller. This correlation between causal estimate and standard error introduces a second source of bias into meta-analysis of Mendelian randomization studies. Bias can be alleviated in meta-analyses by using individual level data and by pooling genetic effects across studies. CONCLUSIONS: Weak instrument bias is of practical importance for the design and analysis of Mendelian randomization studies. Post hoc choice of instruments, genetic models or data based on measured F-statistics can exacerbate bias. In particular, the commonly cited rule of thumb that F > 10 avoids bias in IV analysis is misleading.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“A key point of consideration is the choice of single nucleotide polymorphisms (SNPs) as instrumental variables (IVs) in MR analysis[8,9]. This selection is pivotal, as the potential for linkage disequilibrium and pleiotropy among these SNPs could introduce biases into the analysis.”
From Evaluating genetic insights into ulcerative colitis and anxiety: Limitations and future directions (2024) · cites this paper as [8]
In the citing paper
“Although some estimates were directionally suggestive, they were not robust, reflecting lower power, greater phenotype heterogeneity and limited instrument strength69–71.”
From Genetic trade-offs in fertility and longevity explain the maintenance of disease-associated alleles in humans (2026) · cites this paper as [69]
In the citing paper
“Moreover, two-sample approaches can be used with individual-level data (such as the use of externally-derived weights), and summarized data approaches can be used with one-sample data (if necessary, by creating the summarized data from the individual-level data 37 ).”
From Guidelines for performing Mendelian randomization investigations (2020) · cites this paper as [37]
In the citing paper
“With a sample size of 5000, this corresponds to average F statistics of around 65, so the potential of bias from weak instruments is small.38”
From Network Mendelian randomization: using genetic variants as instrumental variables to investigate mediation in causal pathways. (2015) · cites this paper as [38]
Citations
Cites
Statistical Analysis With Missing Data
Lahiff, M., Little, R. J. A., & Rubin, D. B. (1989) · Journal of the American Statistical Association · doi:10.2307/2289883 · Cited by 17,265
Inflammation, Atherosclerosis, and Coronary Artery Disease
Hansson, G. K. (2005) · New England Journal of Medicine · doi:10.1056/nejmra043430 · Cited by 8,773
Statistical Analysis with Missing Data
Little, R. J. A., & Rubin, D. B. (2002) · Wiley Series in Probability and Statistics · doi:10.1002/9781119013563 · Cited by 8,473
Instrumental Variables Regression with Weak Instruments
Staiger, D., & Stock, J. H. (1997) · Econometrica · doi:10.2307/2171753 · Cited by 7,081
Davey Smith, G., & Ebrahim, S. (2003) · International Journal of Epidemiology · doi:10.1093/ije/dyg070 · Cited by 5,882
Estimation and Inference in Econometrics.
Chambers, M. J., Davidson, R., & MacKinnon, J. G. (1994) · The Economic Journal · doi:10.2307/2234656 · Cited by 5,413
Instrumental Variables Regression with Weak Instruments
Staiger, D., & Stock, J. (1994) · doi:10.3386/t0151 · Cited by 5,302 · cited 4×
“The bias from weak instruments depends on the strength of the instrument through the F statistic [14, 23].”
BackgroundInfluentialMendelian randomization: Using genes as instruments for making causal inferences in epidemiology
Lawlor, D. A., Harbord, R. M., Sterne, J. A. C., Timpson, N., & Davey Smith, G. (2008) · Statistics in Medicine · doi:10.1002/sim.3034 · Cited by 4,618
A Survey of Weak Instruments and Weak Identification in Generalized Method of Moments
Stock, J. H., Wright, J. H., & Yogo, M. (2002) · Journal of Business & Economic Statistics · doi:10.1198/073500102288618658 · Cited by 4,274
Bound, J., Jaeger, D. A., & Baker, R. M. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476536 · Cited by 3,618
Instrumental Variables and GMM: Estimation and Testing
Baum, C. F., Schaffer, M. E., & Stillman, S. (2003) · The Stata Journal: Promoting communications on statistics and Stata · doi:10.1177/1536867x0300300101 · Cited by 2,649
Estimation and Inference in Econometrics.
Levin, A., Davidson, R., & MacKinnon, J. G. (1994) · Journal of the American Statistical Association · doi:10.2307/2290953 · Cited by 2,396
Testing for Weak Instruments in Linear IV Regression
Stock, J., & Yogo, M. (2002) · doi:10.3386/t0284 · Cited by 1,842
Pierce, B. L., Ahsan, H., & VanderWeele, T. J. (2011) · International Journal of Epidemiology · doi:10.1093/ije/dyq151 · Cited by 1,836
Enhanced Routines for Instrumental Variables/Generalized Method of Moments Estimation and Testing
Baum, C. F., Schaffer, M. E., & Stillman, S. (2007) · The Stata Journal: Promoting communications on statistics and Stata · doi:10.1177/1536867x0800700402 · Cited by 1,272
Mendelian randomization: prospects, potentials, and limitations
Smith, G. D. (2004) · International Journal of Epidemiology · doi:10.1093/ije/dyh132 · Cited by 1,222
An introduction to instrumental variables for epidemiologists
Greenland, S. (2000) · International Journal of Epidemiology · doi:10.1093/ije/29.4.722 · Cited by 1,156
Mendelian randomization as an instrumental variable approach to causal inference
Didelez, V., & Sheehan, N. (2007) · Statistical Methods in Medical Research · doi:10.1177/0962280206077743 · Cited by 923
Genetically elevated C-reactive protein and ischemic vascular disease
Zacho, J., Tybjærg-Hansen, A., Jensen, J. S., Grande, P., Sillesen, H., & Nordestgaard, B. G. (2008) · New England Journal of Medicine · doi:10.1056/nejmoa0707402 · Cited by 839
Instrument Relevance in Multivariate Linear Models: A Simple Measure
Shea, J. (1997) · Review of Economics and Statistics · doi:10.1162/rest.1997.79.2.348 · Cited by 824
C Reactive Protein Coronary Heart Disease Genetics Collaboration (CCGC) (2011) · BMJ · doi:10.1136/bmj.d548 · Cited by 642
What can mendelian randomisation tell us about modifiable behavioural and environmental exposures?
Smith, G. D., & Ebrahim, S. (2005) · BMJ · doi:10.1136/bmj.330.7499.1076 · Cited by 545
Instrumental Variables: Application and Limitations
Martens, E. P., Pestman, W. R., de Boer, A., Belitser, S. V., & Klungel, O. H. (2006) · Epidemiology · doi:10.1097/01.ede.0000215160.88317.cb · Cited by 464
Nelson, C. R., & Startz, R. (1990) · The Journal of Business · doi:10.1086/296497 · Cited by 363
Nelson, C., & Startz, R. (1988) · National Bureau of Economic Research · doi:10.3386/t0069 · Cited by 354
Estimation with weak instruments: Accuracy of higher‐order bias and MSE approximations
Hahn, J., Hausman, J., & Kuersteiner, G. (2004) · The Econometrics Journal · doi:10.1111/j.1368-423x.2004.00131.x · Cited by 332
Judging Instrument Relevance in Instrumental Variables Estimation
Hall, A. R., Rudebusch, G. D., & Wilcox, D. W. (1996) · International Economic Review · doi:10.2307/2527324 · Cited by 331
Assumptions of IV Methods for Observational Epidemiology.
Didelez, V., Meng, S., & Sheehan, N. A. (2010) · Statistical Science · doi:10.1214/09-sts316 · Cited by 214
The Exact Sampling Distribution of Ordinary Least Squares and Two-Stage Least Squares Estimators
Sawa, T. (1969) · Journal of the American Statistical Association · doi:10.1080/01621459.1969.10501024 · Cited by 138
The Exact Distribution of a Structural Coefficient Estimator
Richardson, D. H. (1968) · Journal of the American Statistical Association · doi:10.1080/01621459.1968.10480921 · Cited by 135
‘Mendelian randomization’ equals instrumental variable analysis with genetic instruments
Wehby, G. L., Ohsfeldt, R. L., & Murray, J. C. (2008) · Statistics in Medicine · doi:10.1002/sim.3255 · Cited by 97
Meta-analysis of genetic studies using Mendelian randomization—a multivariate approach
Thompson, J. R., Minelli, C., Abrams, K. R., Tobin, M. D., & Riley, R. D. (2005) · Statistics in Medicine · doi:10.1002/sim.2100 · Cited by 96
Estimation of bias in nongenetic observational studies using "mendelian triangulation".
Bautista, L., Smeeth, L., Hingorani, A., & Casas, J. (2006) · Annals of Epidemiology · doi:10.1016/j.annepidem.2006.02.001 · Cited by 78
Zohoori, N., & Savitz, D. A. (1997) · Annals of Epidemiology · doi:10.1016/s1047-2797(97)00023-9 · Cited by 74
Chapter 4. Instrumental Variables in Action: Sometimes You Get What You Need
Angrist, J. D., & Pischke, J. (2008) · Princeton University Press eBooks · doi:10.1515/9781400829828-009 · Cited by 66
CRP CHD Genetics Collaboration (2008) · European Journal of Epidemiology · doi:10.1007/s10654-008-9249-z · Cited by 59
Self-citationBurgess, S., & Thompson, S. G. (2010) · Statistics in Medicine · doi:10.1002/sim.3843 · Cited by 31
Self-citation
Research works printed but not linked: 2
- Hayashi, 2000, Econometrics
- Baum, 2006, An introduction to modern econometrics using Stata (p188)
Cited by
Bowden, J., Davey Smith, G., & Burgess, S. (2015) · International Journal of Epidemiology · doi:10.1093/ije/dyv080 · Cited by 9,816
Self-citationBowden, J., Davey Smith, G., Haycock, P. C., & Burgess, S. (2016) · Genetic Epidemiology · doi:10.1002/gepi.21965 · Cited by 8,922
“…were obtained, then the resulting analysis suffers from bias and inflated type 1 error rates when the included variants are “weak” (i.e., they do not explain a substantial proportion of variation in the exposure in the dataset under analysis) (Burgess et al., 2011; Pierce and Burgess, 2013).”
BackgroundSelf-citationThe MR-Base platform supports systematic causal inference across the human phenome
Hemani, G., Zheng, J., Elsworth, B., Wade, K. H., Haberland, V., Baird, D., Laurin, C., Burgess, S., Bowden, J., Langdon, R., et al. (2018) · eLife · doi:10.7554/elife.34408 · Cited by 7,959
Self-citationMendelian Randomization Analysis With Multiple Genetic Variants Using Summarized Data
Burgess, S., Butterworth, A., & Thompson, S. G. (2013) · Genetic Epidemiology · doi:10.1002/gepi.21758 · Cited by 6,050
Self-citationAn atlas of genetic correlations across human diseases and traits
ReproGen Consortium, Bulik-Sullivan, B., Psychiatric Genomics Consortium, Genetic Consortium for Anorexia Nervosa of the Wellcome Trust Case Control Consortium 3, Finucane, H. K., Anttila, V., Gusev, A., Day, F. R., Loh, P.-R., Duncan, L., et al. (2015) · Nature Genetics · doi:10.1038/ng.3406 · Cited by 4,255
Metadata
- Authors
- Burgess, S., Thompson, S. G., & CRP CHD Genetics Collaboration
- Affiliations
- University of Cambridge (GB)
- Venue
- International Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2011-03-16
- Volume
- 40
- Issue
- 3
- Pages
- 755-764
- ISSN
- 0300-5771 (ISSN-L)
- 1464-3685
- OpenAlex
- W2127768736
- Cited by
- 3,952
- References
- 40
- Citations by year
- 2026: 432 · 2025: 999 · 2024: 1393 · 2023: 545 · 2022: 213 · 2021: 133 · 2020: 75 · 2019: 37 · 2018: 41 · 2017: 16 · 2016: 18 · 2015: 13 · 2014: 15 · 2013: 11 · 2012: 4
- FWCI
- 6.59
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- International Journal of Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- HighWire Press Open Archive (submittedVersion)
- Funders
- British Heart Foundation (SP/08/007/23628, RG/07/008/23674, RG/08/014/24067)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic Associations and Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Keywords
- weak instrument bias, Mendelian randomization, instrumental variables, F-statistic, confounding, C-reactive protein, fibrinogen, microdata, causal inference
- MeSH terms
- Data Interpretation, Statistical, Female, Genotype, Humans, Male, Random Allocation, Sensitivity and Specificity, Genetic Variation, Bias, Confounding Factors, Epidemiologic, Genetic Predisposition to Disease, Mendelian Randomization Analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.