Using the global randomization test as a Mendelian randomization falsification test for the exclusion restriction assumption

Mendelian randomization may give biased causal estimates if the instrument affects the outcome not solely via the exposure of interest (violating the exclusion restriction assumption). We demonstrate use of a global randomization test as a falsification test for the exclusion restriction assumption....

Full description

Saved in:
Bibliographic Details
Published in:European journal of epidemiology 2024-08, Vol.39 (8), p.843-855
Main Authors: Millard, Louise A. C., Davey Smith, George, Tilling, Kate
Format: Article
Language:English
Subjects:
Bias
Cardiology
Cardiovascular disease
Cardiovascular diseases
Coronary artery disease
Epidemiology
Genetic diversity
Genetic variance
Heart diseases
Infectious Diseases
Medicine
Medicine & Public Health
Methods
Oncology
Permutations
Pleiotropy
Public Health
Randomization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c475t-891c2dbe1aa7e63f8be34c0e42df97baa07d4a864178b6096905d23e1be4357f3
cites cdi_FETCH-LOGICAL-c475t-891c2dbe1aa7e63f8be34c0e42df97baa07d4a864178b6096905d23e1be4357f3
container_end_page 855
container_issue 8
container_start_page 843
container_title European journal of epidemiology
container_volume 39
creator Millard, Louise A. C.
Davey Smith, George
Tilling, Kate
description Mendelian randomization may give biased causal estimates if the instrument affects the outcome not solely via the exposure of interest (violating the exclusion restriction assumption). We demonstrate use of a global randomization test as a falsification test for the exclusion restriction assumption. Using simulations, we explored the statistical power of the randomization test to detect an association between a genetic instrument and a covariate set due to (a) selection bias or (b) horizontal pleiotropy, compared to three approaches examining associations with individual covariates: (i) Bonferroni correction for the number of covariates, (ii) correction for the effective number of independent covariates, and (iii) an r 2 permutation-based approach. We conducted proof-of-principle analyses in UK Biobank, using CRP as the exposure and coronary heart disease (CHD) as the outcome. In simulations, power of the randomization test was higher than the other approaches for detecting selection bias when the correlation between the covariates was low (r 2  
doi_str_mv 10.1007/s10654-024-01097-6
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11410989</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3106525824</sourcerecordid><originalsourceid>FETCH-LOGICAL-c475t-891c2dbe1aa7e63f8be34c0e42df97baa07d4a864178b6096905d23e1be4357f3</originalsourceid><addsrcrecordid>eNp9kUtv1TAQhS1ERS-FP8ACRWLDJnT8iu0VQhUvqVU3dG05yeTWVWJf7AQB4sfj3FtK6YKFZWvmm2MfH0JeUHhDAdRpptBIUQMri4JRdfOIbKhUvFZMi8dkA9zwmhkDx-RpzjcAoMHIJ-SYa8Go0HJDfl1lH7bVfI3VdoytG6vkQh8n_9PNPoZqxjxXLleuusDQ4-hdeEAMbsx-8N09fohpr4jfu3HJazmVcvLdHnE5L9NuPT4jR-s0Pr_dT8jVh_dfzj7V55cfP5-9O687oeRca0M71rdInVPY8EG3yEUHKFg_GNU6B6oXTjeCKt02YBoDsmccaYuCSzXwE_L2oLtb2gn7DsOc3Gh3yU8u_bDReftvJ_hru43fLKWifKw2ReH1rUKKX5dixk4-dziOLmBcsmWGc9FQULKgrx6gN3FJofizfA2MSc1EodiB6lLMOeFw9xoKdk3XHtK1JV27T9c2ZejlfR93I3_iLAA_ALm0whbT37v_I_sbp1ezug</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3106525824</pqid></control><display><type>article</type><title>Using the global randomization test as a Mendelian randomization falsification test for the exclusion restriction assumption</title><source>Springer Link</source><creator>Millard, Louise A. C. ; Davey Smith, George ; Tilling, Kate</creator><creatorcontrib>Millard, Louise A. C. ; Davey Smith, George ; Tilling, Kate</creatorcontrib><description>Mendelian randomization may give biased causal estimates if the instrument affects the outcome not solely via the exposure of interest (violating the exclusion restriction assumption). We demonstrate use of a global randomization test as a falsification test for the exclusion restriction assumption. Using simulations, we explored the statistical power of the randomization test to detect an association between a genetic instrument and a covariate set due to (a) selection bias or (b) horizontal pleiotropy, compared to three approaches examining associations with individual covariates: (i) Bonferroni correction for the number of covariates, (ii) correction for the effective number of independent covariates, and (iii) an r 2 permutation-based approach. We conducted proof-of-principle analyses in UK Biobank, using CRP as the exposure and coronary heart disease (CHD) as the outcome. In simulations, power of the randomization test was higher than the other approaches for detecting selection bias when the correlation between the covariates was low (r 2  &lt; 0.1), and at least as powerful as the other approaches across all simulated horizontal pleiotropy scenarios. In our applied example, we found strong evidence of selection bias using all approaches (e.g., global randomization test p  &lt; 0.002). We identified 51 of the 58 CRP genetic variants as horizontally pleiotropic, and estimated effects of CRP on CHD attenuated somewhat to the null when excluding these from the genetic risk score (OR = 0.96 [95% CI: 0.92, 1.00] versus 0.97 [95% CI: 0.90, 1.05] per 1-unit higher log CRP levels). The global randomization test can be a useful addition to the MR researcher’s toolkit.</description><identifier>ISSN: 0393-2990</identifier><identifier>ISSN: 1573-7284</identifier><identifier>EISSN: 1573-7284</identifier><identifier>DOI: 10.1007/s10654-024-01097-6</identifier><identifier>PMID: 38421485</identifier><language>eng</language><publisher>Dordrecht: Springer Netherlands</publisher><subject>Bias ; Cardiology ; Cardiovascular disease ; Cardiovascular diseases ; Coronary artery disease ; Epidemiology ; Genetic diversity ; Genetic variance ; Heart diseases ; Infectious Diseases ; Medicine ; Medicine &amp; Public Health ; Methods ; Oncology ; Permutations ; Pleiotropy ; Public Health ; Randomization</subject><ispartof>European journal of epidemiology, 2024-08, Vol.39 (8), p.843-855</ispartof><rights>The Author(s) 2024</rights><rights>2024. The Author(s).</rights><rights>The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>The Author(s) 2024 2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c475t-891c2dbe1aa7e63f8be34c0e42df97baa07d4a864178b6096905d23e1be4357f3</citedby><cites>FETCH-LOGICAL-c475t-891c2dbe1aa7e63f8be34c0e42df97baa07d4a864178b6096905d23e1be4357f3</cites><orcidid>0000-0002-1010-8926 ; 0000-0003-4787-8411 ; 0000-0002-1407-8314</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38421485$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Millard, Louise A. C.</creatorcontrib><creatorcontrib>Davey Smith, George</creatorcontrib><creatorcontrib>Tilling, Kate</creatorcontrib><title>Using the global randomization test as a Mendelian randomization falsification test for the exclusion restriction assumption</title><title>European journal of epidemiology</title><addtitle>Eur J Epidemiol</addtitle><addtitle>Eur J Epidemiol</addtitle><description>Mendelian randomization may give biased causal estimates if the instrument affects the outcome not solely via the exposure of interest (violating the exclusion restriction assumption). We demonstrate use of a global randomization test as a falsification test for the exclusion restriction assumption. Using simulations, we explored the statistical power of the randomization test to detect an association between a genetic instrument and a covariate set due to (a) selection bias or (b) horizontal pleiotropy, compared to three approaches examining associations with individual covariates: (i) Bonferroni correction for the number of covariates, (ii) correction for the effective number of independent covariates, and (iii) an r 2 permutation-based approach. We conducted proof-of-principle analyses in UK Biobank, using CRP as the exposure and coronary heart disease (CHD) as the outcome. In simulations, power of the randomization test was higher than the other approaches for detecting selection bias when the correlation between the covariates was low (r 2  &lt; 0.1), and at least as powerful as the other approaches across all simulated horizontal pleiotropy scenarios. In our applied example, we found strong evidence of selection bias using all approaches (e.g., global randomization test p  &lt; 0.002). We identified 51 of the 58 CRP genetic variants as horizontally pleiotropic, and estimated effects of CRP on CHD attenuated somewhat to the null when excluding these from the genetic risk score (OR = 0.96 [95% CI: 0.92, 1.00] versus 0.97 [95% CI: 0.90, 1.05] per 1-unit higher log CRP levels). The global randomization test can be a useful addition to the MR researcher’s toolkit.</description><subject>Bias</subject><subject>Cardiology</subject><subject>Cardiovascular disease</subject><subject>Cardiovascular diseases</subject><subject>Coronary artery disease</subject><subject>Epidemiology</subject><subject>Genetic diversity</subject><subject>Genetic variance</subject><subject>Heart diseases</subject><subject>Infectious Diseases</subject><subject>Medicine</subject><subject>Medicine &amp; Public Health</subject><subject>Methods</subject><subject>Oncology</subject><subject>Permutations</subject><subject>Pleiotropy</subject><subject>Public Health</subject><subject>Randomization</subject><issn>0393-2990</issn><issn>1573-7284</issn><issn>1573-7284</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kUtv1TAQhS1ERS-FP8ACRWLDJnT8iu0VQhUvqVU3dG05yeTWVWJf7AQB4sfj3FtK6YKFZWvmm2MfH0JeUHhDAdRpptBIUQMri4JRdfOIbKhUvFZMi8dkA9zwmhkDx-RpzjcAoMHIJ-SYa8Go0HJDfl1lH7bVfI3VdoytG6vkQh8n_9PNPoZqxjxXLleuusDQ4-hdeEAMbsx-8N09fohpr4jfu3HJazmVcvLdHnE5L9NuPT4jR-s0Pr_dT8jVh_dfzj7V55cfP5-9O687oeRca0M71rdInVPY8EG3yEUHKFg_GNU6B6oXTjeCKt02YBoDsmccaYuCSzXwE_L2oLtb2gn7DsOc3Gh3yU8u_bDReftvJ_hru43fLKWifKw2ReH1rUKKX5dixk4-dziOLmBcsmWGc9FQULKgrx6gN3FJofizfA2MSc1EodiB6lLMOeFw9xoKdk3XHtK1JV27T9c2ZejlfR93I3_iLAA_ALm0whbT37v_I_sbp1ezug</recordid><startdate>20240801</startdate><enddate>20240801</enddate><creator>Millard, Louise A. C.</creator><creator>Davey Smith, George</creator><creator>Tilling, Kate</creator><general>Springer Netherlands</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QL</scope><scope>7T2</scope><scope>7TK</scope><scope>7TS</scope><scope>7U7</scope><scope>7U9</scope><scope>C1K</scope><scope>H94</scope><scope>K9.</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-1010-8926</orcidid><orcidid>https://orcid.org/0000-0003-4787-8411</orcidid><orcidid>https://orcid.org/0000-0002-1407-8314</orcidid></search><sort><creationdate>20240801</creationdate><title>Using the global randomization test as a Mendelian randomization falsification test for the exclusion restriction assumption</title><author>Millard, Louise A. C. ; Davey Smith, George ; Tilling, Kate</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c475t-891c2dbe1aa7e63f8be34c0e42df97baa07d4a864178b6096905d23e1be4357f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Bias</topic><topic>Cardiology</topic><topic>Cardiovascular disease</topic><topic>Cardiovascular diseases</topic><topic>Coronary artery disease</topic><topic>Epidemiology</topic><topic>Genetic diversity</topic><topic>Genetic variance</topic><topic>Heart diseases</topic><topic>Infectious Diseases</topic><topic>Medicine</topic><topic>Medicine &amp; Public Health</topic><topic>Methods</topic><topic>Oncology</topic><topic>Permutations</topic><topic>Pleiotropy</topic><topic>Public Health</topic><topic>Randomization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Millard, Louise A. C.</creatorcontrib><creatorcontrib>Davey Smith, George</creatorcontrib><creatorcontrib>Tilling, Kate</creatorcontrib><collection>SpringerOpen</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Health and Safety Science Abstracts (Full archive)</collection><collection>Neurosciences Abstracts</collection><collection>Physical Education Index</collection><collection>Toxicology Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>European journal of epidemiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Millard, Louise A. C.</au><au>Davey Smith, George</au><au>Tilling, Kate</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Using the global randomization test as a Mendelian randomization falsification test for the exclusion restriction assumption</atitle><jtitle>European journal of epidemiology</jtitle><stitle>Eur J Epidemiol</stitle><addtitle>Eur J Epidemiol</addtitle><date>2024-08-01</date><risdate>2024</risdate><volume>39</volume><issue>8</issue><spage>843</spage><epage>855</epage><pages>843-855</pages><issn>0393-2990</issn><issn>1573-7284</issn><eissn>1573-7284</eissn><abstract>Mendelian randomization may give biased causal estimates if the instrument affects the outcome not solely via the exposure of interest (violating the exclusion restriction assumption). We demonstrate use of a global randomization test as a falsification test for the exclusion restriction assumption. Using simulations, we explored the statistical power of the randomization test to detect an association between a genetic instrument and a covariate set due to (a) selection bias or (b) horizontal pleiotropy, compared to three approaches examining associations with individual covariates: (i) Bonferroni correction for the number of covariates, (ii) correction for the effective number of independent covariates, and (iii) an r 2 permutation-based approach. We conducted proof-of-principle analyses in UK Biobank, using CRP as the exposure and coronary heart disease (CHD) as the outcome. In simulations, power of the randomization test was higher than the other approaches for detecting selection bias when the correlation between the covariates was low (r 2  &lt; 0.1), and at least as powerful as the other approaches across all simulated horizontal pleiotropy scenarios. In our applied example, we found strong evidence of selection bias using all approaches (e.g., global randomization test p  &lt; 0.002). We identified 51 of the 58 CRP genetic variants as horizontally pleiotropic, and estimated effects of CRP on CHD attenuated somewhat to the null when excluding these from the genetic risk score (OR = 0.96 [95% CI: 0.92, 1.00] versus 0.97 [95% CI: 0.90, 1.05] per 1-unit higher log CRP levels). The global randomization test can be a useful addition to the MR researcher’s toolkit.</abstract><cop>Dordrecht</cop><pub>Springer Netherlands</pub><pmid>38421485</pmid><doi>10.1007/s10654-024-01097-6</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0002-1010-8926</orcidid><orcidid>https://orcid.org/0000-0003-4787-8411</orcidid><orcidid>https://orcid.org/0000-0002-1407-8314</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0393-2990
ispartof European journal of epidemiology, 2024-08, Vol.39 (8), p.843-855
issn 0393-2990
1573-7284
1573-7284
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11410989
source Springer Link
subjects Bias
Cardiology
Cardiovascular disease
Cardiovascular diseases
Coronary artery disease
Epidemiology
Genetic diversity
Genetic variance
Heart diseases
Infectious Diseases
Medicine
Medicine & Public Health
Methods
Oncology
Permutations
Pleiotropy
Public Health
Randomization
title Using the global randomization test as a Mendelian randomization falsification test for the exclusion restriction assumption
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T15%3A41%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Using%20the%20global%20randomization%20test%20as%20a%20Mendelian%20randomization%20falsification%20test%20for%20the%20exclusion%20restriction%20assumption&rft.jtitle=European%20journal%20of%20epidemiology&rft.au=Millard,%20Louise%20A.%20C.&rft.date=2024-08-01&rft.volume=39&rft.issue=8&rft.spage=843&rft.epage=855&rft.pages=843-855&rft.issn=0393-2990&rft.eissn=1573-7284&rft_id=info:doi/10.1007/s10654-024-01097-6&rft_dat=%3Cproquest_pubme%3E3106525824%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c475t-891c2dbe1aa7e63f8be34c0e42df97baa07d4a864178b6096905d23e1be4357f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3106525824&rft_id=info:pmid/38421485&rfr_iscdi=true