Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

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

Fernando Pires Hartwig1,2, George Davey Smith2,3, Jack Bowden2,3

  • 1Postgraduate Program in Epidemiology, Federal University of Pelotas, Pelotas, Brazil.

International Journal of Epidemiology
|October 18, 2017
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Prevalence, Perpetrators, and Patterns of Violence in Pelotas, Brazil: A Cross-Cohort Analysis Over Four Decades.

Journal of interpersonal violence·2026
Same author

Empirically Assessing the Plausibility of Unconfoundedness in Observational Studies.

Epidemiology (Cambridge, Mass.)·2026
Same author

The double-burden of poverty on cognition hypothesis: a systematic review of the mechanisms of the effect of poverty in early life on the development and expression of cognition in adolescence and adulthood.

Social psychiatry and psychiatric epidemiology·2026
Same author

Lessons from 13 years of accelerometry measurements in five Brazilian cohorts: methodological aspects.

Cadernos de saude publica·2025
Same author

How to use directed acyclic graphs: guide for clinical researchers.

BMJ (Clinical research ed.)·2025
Same author

Trans-ancestry genome-wide association study of childhood body mass index identifies novel loci and age-specific effects.

HGG advances·2025

The mode-based estimate (MBE) offers a new Mendelian randomization (MR) method for causal inference, showing reduced bias and errors. This approach is valuable for analyzing genetic data from large genome-wide association studies (GWAS).

Area of Science:

  • Genetics
  • Epidemiology
  • Statistical genetics

Background:

  • Mendelian randomization (MR) is increasingly used to strengthen causal inference in observational studies.
  • Summary data methods in MR, particularly two-sample designs, leverage large genome-wide association studies (GWAS) data.
  • Advanced MR methods like MR-Egger and weighted median relax traditional instrumental variable assumptions.

Purpose of the Study:

  • Introduce a novel method, the mode-based estimate (MBE), for causal effect estimation using multiple genetic instruments.
  • Establish the consistency of MBE when a majority of instruments may be invalid.
  • Evaluate MBE's performance in simulations and its application to lipid fractions, urate levels, and coronary heart disease risk.

Main Methods:

  • The mode-based estimate (MBE) is proposed for single causal effect estimation from multiple genetic instruments.
Keywords:
CausalityMendelian randomizationgenetic pleiotropygenetic variationinstrumental variables

Related Experiment Videos

  • MBE's consistency is achieved when the plurality of individual-instrument estimates derive from valid instruments.
  • Simulations mimic two-sample summary data settings to assess MBE performance.

    • Main Results:

    • The MBE demonstrated reduced bias and lower Type I error rates compared to other methods under null conditions.
    • MBE's statistical power was lower than Inverse Variance Weighting (IVW) and weighted median but higher than MR-Egger regression.
    • The method's sample size requirements are compatible with typical GWAS consortia data.

    Conclusions:

    • The mode-based estimate (MBE) provides a valuable tool by relaxing instrumental variable assumptions in Mendelian randomization.
    • MBE should be integrated with other methods for comprehensive sensitivity analyses in genetic research.
    • This method enhances causal inference capabilities using summary-level GWAS data.