{
  "name": "TwoSampleMR Estimation Methods and Model Assumptions",
  "description": "Comparative specifications of Mendelian randomization statistical estimation methods implemented in the TwoSampleMR R package, detailing instrumental variable assumptions, minimum instrument counts, breakdown thresholds, and primary methodological citations.",
  "page": "https://casrai.org/guides/twosamplemr",
  "publisher": "CASRAI",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "dateModified": "2026-11-16T15:57:01Z",
  "temporalCoverage": null,
  "spatialCoverage": null,
  "columns": [
    {
      "name": "Method Name",
      "unit": "",
      "description": "Name of the Mendelian randomization estimator"
    },
    {
      "name": "TwoSampleMR Function",
      "unit": "",
      "description": "Specific method identifier used in mr(method_list=...)"
    },
    {
      "name": "Minimum Instruments",
      "unit": "SNPs",
      "description": "Minimum number of genetic variants required"
    },
    {
      "name": "InSIDE Required",
      "unit": "",
      "description": "Whether the method requires the Instrument Strength Independent of Direct Effect assumption"
    },
    {
      "name": "Breakdown Threshold",
      "unit": "%",
      "description": "Maximum proportion of invalid or pleiotropic instruments tolerated"
    },
    {
      "name": "Primary Reference",
      "unit": "",
      "description": "Foundational methodology publication"
    }
  ],
  "rows": [
    {
      "Method Name": "Wald Ratio",
      "TwoSampleMR Function": "mr_wald_ratio",
      "Minimum Instruments": 1,
      "InSIDE Required": "No (single instrument)",
      "Breakdown Threshold": 0,
      "Primary Reference": "Burgess et al. (2013)"
    },
    {
      "Method Name": "Inverse Variance Weighted (Fixed Effects)",
      "TwoSampleMR Function": "mr_ivw_fe",
      "Minimum Instruments": 2,
      "InSIDE Required": "Yes (zero pleiotropy)",
      "Breakdown Threshold": 0,
      "Primary Reference": "Burgess et al. (2013)"
    },
    {
      "Method Name": "Inverse Variance Weighted (Multiplicative Random Effects)",
      "TwoSampleMR Function": "mr_ivw_mre",
      "Minimum Instruments": 2,
      "InSIDE Required": "Yes (balanced pleiotropy)",
      "Breakdown Threshold": 0,
      "Primary Reference": "Burgess et al. (2013)"
    },
    {
      "Method Name": "MR-Egger Regression",
      "TwoSampleMR Function": "mr_egger_regression",
      "Minimum Instruments": 3,
      "InSIDE Required": "Yes (directional pleiotropy allowed)",
      "Breakdown Threshold": 0,
      "Primary Reference": "Bowden et al. (2015)"
    },
    {
      "Method Name": "Weighted Median Estimator",
      "TwoSampleMR Function": "mr_weighted_median",
      "Minimum Instruments": 3,
      "InSIDE Required": "No",
      "Breakdown Threshold": 50,
      "Primary Reference": "Bowden et al. (2016)"
    },
    {
      "Method Name": "Simple Median Estimator",
      "TwoSampleMR Function": "mr_simple_median",
      "Minimum Instruments": 3,
      "InSIDE Required": "No",
      "Breakdown Threshold": 50,
      "Primary Reference": "Bowden et al. (2016)"
    },
    {
      "Method Name": "Weighted Mode Estimator",
      "TwoSampleMR Function": "mr_weighted_mode",
      "Minimum Instruments": 3,
      "InSIDE Required": "No",
      "Breakdown Threshold": 50,
      "Primary Reference": "Hartwig et al. (2017)"
    },
    {
      "Method Name": "Simple Mode Estimator",
      "TwoSampleMR Function": "mr_simple_mode",
      "Minimum Instruments": 3,
      "InSIDE Required": "No",
      "Breakdown Threshold": 50,
      "Primary Reference": "Hartwig et al. (2017)"
    }
  ],
  "sources": [
    {
      "title": "The MR-Base platform supports systematic causal inference across the human phenome",
      "url": "https://doi.org/10.7554/eLife.34408",
      "accessed": "2026-11-16"
    },
    {
      "title": "TwoSampleMR Package Reference: mr() Function",
      "url": "https://mrcieu.github.io/TwoSampleMR/reference/mr.html",
      "accessed": "2026-11-16"
    },
    {
      "title": "Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression",
      "url": "https://doi.org/10.1093/ije/dyv080",
      "accessed": "2026-11-16"
    },
    {
      "title": "Consistent Estimation in Mendelian Randomization with Some Invalid Instruments Using a Weighted Median Estimator",
      "url": "https://doi.org/10.1002/gepi.21965",
      "accessed": "2026-11-16"
    },
    {
      "title": "Mendelian randomization analysis with multiple genetic variants using summarized data",
      "url": "https://doi.org/10.1002/gepi.21758",
      "accessed": "2026-11-16"
    }
  ]
}