Correct standard errors can bias meta‐analysis
Partial correlation coefficients are often used as effect sizes in the meta‐analysis and systematic review of multiple regression analysis research results. There are two well‐known formulas for the variance and thereby for the standard error (SE) of partial correlation coefficients (PCC). One is co...
Saved in:
Published in | Research synthesis methods Vol. 14; no. 3; pp. 515 - 519 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
England
Wiley
01.05.2023
Wiley Subscription Services, Inc |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Partial correlation coefficients are often used as effect sizes in the meta‐analysis and systematic review of multiple regression analysis research results. There are two well‐known formulas for the variance and thereby for the standard error (SE) of partial correlation coefficients (PCC). One is considered the “correct” variance in the sense that it better reflects the variation of the sampling distribution of partial correlation coefficients. The second is used to test whether the population PCC is zero, and it reproduces the test statistics and the p‐values of the original multiple regression coefficient that PCC is meant to represent. Simulations show that the “correct” PCC variance causes random effects to be more biased than the alternative variance formula. Meta‐analyses produced by this alternative formula statistically dominate those that use “correct” SEs. Meta‐analysts should never use the “correct” formula for partial correlations' standard errors. |
---|---|
AbstractList | Partial correlation coefficients are often used as effect sizes in the meta-analysis and systematic review of multiple regression analysis research results. There are two well-known formulas for the variance and thereby for the standard error (SE) of partial correlation coefficients (PCC). One is considered the "correct" variance in the sense that it better reflects the variation of the sampling distribution of partial correlation coefficients. The second is used to test whether the population PCC is zero, and it reproduces the test statistics and the p-values of the original multiple regression coefficient that PCC is meant to represent. Simulations show that the "correct" PCC variance causes random effects to be more biased than the alternative variance formula. Meta-analyses produced by this alternative formula statistically dominate those that use "correct" SEs. Meta-analysts should never use the "correct" formula for partial correlations' standard errors. Partial correlation coefficients are often used as effect sizes in the meta‐analysis and systematic review of multiple regression analysis research results. There are two well‐known formulas for the variance and thereby for the standard error (SE) of partial correlation coefficients (PCC). One is considered the “correct” variance in the sense that it better reflects the variation of the sampling distribution of partial correlation coefficients. The second is used to test whether the population PCC is zero, and it reproduces the test statistics and the p ‐values of the original multiple regression coefficient that PCC is meant to represent. Simulations show that the “correct” PCC variance causes random effects to be more biased than the alternative variance formula. Meta‐analyses produced by this alternative formula statistically dominate those that use “correct” SEs. Meta‐analysts should never use the “correct” formula for partial correlations' standard errors. |
Author | Doucouliagos, Hristos Stanley, T. D. |
Author_xml | – sequence: 1 givenname: T. D. surname: Stanley fullname: Stanley, T. D. email: tom.stanley1@deakin.edu.au organization: Deakin University – sequence: 2 givenname: Hristos surname: Doucouliagos fullname: Doucouliagos, Hristos organization: Deakin University |
BackLink | http://eric.ed.gov/ERICWebPortal/detail?accno=EJ1376273$$DView record in ERIC https://www.ncbi.nlm.nih.gov/pubmed/36880162$$D View this record in MEDLINE/PubMed |
BookMark | eNp10MtKw0AUBuBBKrbWLnwAJeBGF23nkrktpdRLqQhe1uEkOYGUXOpMinTnI_iMPomprV0IzmYG_o9zhv-YdKq6QkJOGR0xSvl44Xw5YkqwA9JjWtohN0Z39m9tu2Tg_YK2R1jFlT4iXaGMoUzxHqGT2jlMmsA3UKXg0gCdq50PEqiCOAcflNjA18cnVFCsfe5PyGEGhcfB7u6T15vpy-RuOH-8vZ9cz4dJyCgbxsxKmVDGBcoQJUhpdawQGQfOreaSZQgQxxZVFmsplbUGjACQImVpqEWfXG7nLl39tkLfRGXuEywKqLBe-YhrEwqjQyVbevGHLuqVa__bKkNtKLmlYauutipxtfcOs2jp8hLcOmI02jQZbZqMNk229nw3cRWXmO7lb28tONsCdHmyj6czJrTiWrT5eJu_5wWu_98UzZ6eH35WfgN0i4dA |
CitedBy_id | crossref_primary_10_1002_jrsm_1697 crossref_primary_10_1002_jrsm_1654 crossref_primary_10_1111_joes_12595 crossref_primary_10_1002_jrsm_1704 |
Cites_doi | 10.5243/jsswr.2013.24 10.1111/obes.12240 10.1080/01621459.1961.10482120 10.1002/jrsm.1632 10.1002/jrsm.1512 10.1016/j.irfa.2018.11.006 10.3102/10769986021004299 10.1257/app.20150044 10.1037/met0000025 10.1002/sim.6481 10.1177/1740774507079441 10.4324/9780203111710 10.1093/jeea/jvac053 |
ContentType | Journal Article |
Copyright | 2023 The Authors. published by John Wiley & Sons Ltd. 2023 The Authors. Research Synthesis Methods published by John Wiley & Sons Ltd. 2023. This article is published under http://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2023 The Authors. published by John Wiley & Sons Ltd. – notice: 2023 The Authors. Research Synthesis Methods published by John Wiley & Sons Ltd. – notice: 2023. This article is published under http://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 24P WIN 7SW BJH BNH BNI BNJ BNO ERI PET REK WWN CGR CUY CVF ECM EIF NPM AAYXX CITATION 7X8 |
DOI | 10.1002/jrsm.1631 |
DatabaseName | Wiley Online Library Open Access Wiley-Blackwell Open Access Backfiles ERIC ERIC (Ovid) ERIC ERIC ERIC (Legacy Platform) ERIC( SilverPlatter ) ERIC ERIC PlusText (Legacy Platform) Education Resources Information Center (ERIC) ERIC Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed CrossRef MEDLINE - Academic |
DatabaseTitle | ERIC MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) CrossRef MEDLINE - Academic |
DatabaseTitleList | MEDLINE CrossRef ERIC |
Database_xml | – sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database – sequence: 4 dbid: ERI name: ERIC url: https://eric.ed.gov/ sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Sciences (General) |
EISSN | 1759-2887 |
ERIC | EJ1376273 |
EndPage | 519 |
ExternalDocumentID | 10_1002_jrsm_1631 36880162 EJ1376273 JRSM1631 |
Genre | commentary Journal Article |
GroupedDBID | 05W 0R~ 1OC 24P 31~ 33P 4.4 50Y 5DZ 8-0 8-1 8UM A00 AAESR AAHHS AANLZ AAZKR ABCUV ABDBF ABIVO ABJNI ABLJU ACBWZ ACCFJ ACCZN ACGFS ACIWK ACPOU ACXQS ADBBV ADKYN ADXAS ADZMN AEEZP AEIGN AENEX AEQDE AEUYR AFBPY AFFPM AFZJQ AHBTC AITYG AIURR AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN AMYDB ASPBG AVWKF AZFZN AZVAB BDRZF BFHJK BMXJE BRXPI D-A DCZOG EBS EJD FEDTE G-S GODZA HGLYW HVGLF HZ~ LATKE LEEKS LH4 LITHE LOXES LUTES LW6 LYRES MEWTI MY. MY~ O9- P2W P4E PQQKQ ROL RX1 SUPJJ WBKPD WIN WOHZO WXSBR WYJ ZZTAW 09C 7SW ACDLN ACRPL ACYXJ BJH BNH BNI BNJ BNO ERI PET REK WWN CGR CUY CVF ECM EIF NPM AAYXX CITATION 7X8 |
ID | FETCH-LOGICAL-c4101-b1955c0123e54e5a5597b6ee12a2297251feaabb9e6fb7556998a83aa53d1d473 |
IEDL.DBID | 24P |
ISSN | 1759-2879 |
IngestDate | Wed Jul 24 11:32:51 EDT 2024 Thu Dec 12 19:18:19 EST 2024 Fri Dec 06 03:49:00 EST 2024 Sat Sep 28 08:17:52 EDT 2024 Tue Dec 10 19:21:04 EST 2024 Sat Aug 24 00:47:17 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 3 |
Keywords | meta-analysis partial correlation coefficients bias mean square errors |
Language | English |
License | Attribution-NonCommercial 2023 The Authors. Research Synthesis Methods published by John Wiley & Sons Ltd. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c4101-b1955c0123e54e5a5597b6ee12a2297251feaabb9e6fb7556998a83aa53d1d473 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
OpenAccessLink | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fjrsm.1631 |
PMID | 36880162 |
PQID | 2809452904 |
PQPubID | 1046372 |
PageCount | 5 |
ParticipantIDs | proquest_miscellaneous_2784387465 proquest_journals_2809452904 crossref_primary_10_1002_jrsm_1631 pubmed_primary_36880162 eric_primary_EJ1376273 wiley_primary_10_1002_jrsm_1631_JRSM1631 |
PublicationCentury | 2000 |
PublicationDate | May 2023 2023-05-00 2023-May 20230501 |
PublicationDateYYYYMMDD | 2023-05-01 |
PublicationDate_xml | – month: 05 year: 2023 text: May 2023 |
PublicationDecade | 2020 |
PublicationPlace | England |
PublicationPlace_xml | – name: England – name: Chichester |
PublicationTitle | Research synthesis methods |
PublicationTitleAlternate | Res Synth Methods |
PublicationYear | 2023 |
Publisher | Wiley Wiley Subscription Services, Inc |
Publisher_xml | – sequence: 0 name: Wiley – sequence: 0 name: Wiley Subscription Services, Inc |
References | 2015; 34 2023; 14 2013; 4 2021; 12 2019; 61 2012 2022 2022; 5 2015; 20 1976 2018; 80 2007; 4 2003 1961; 56 2016; 8 1996; 21 e_1_2_7_5_1 e_1_2_7_4_1 e_1_2_7_3_1 e_1_2_7_9_1 e_1_2_7_8_1 e_1_2_7_7_1 e_1_2_7_16_1 e_1_2_7_2_1 e_1_2_7_14_1 e_1_2_7_13_1 e_1_2_7_12_1 Wooldridge JM (e_1_2_7_17_1) 2003 e_1_2_7_11_1 e_1_2_7_10_1 Olkin I (e_1_2_7_6_1) 1976 Stanley TD (e_1_2_7_15_1) 2022; 5 |
References_xml | – start-page: 1 year: 2022 end-page: 36 article-title: The significance of data‐sharing policy publication-title: J Eur Econ Ass – volume: 12 start-page: 776 year: 2021 end-page: 795 article-title: Detecting publication selection bias through excess statistical significance publication-title: Res Synth Methods – volume: 21 start-page: 299 year: 1996 end-page: 332 article-title: Estimating effect size under publication bias: small sample properties and robustness of a random effects selection model publication-title: J Educ Behav Stat – volume: 5 start-page: 1 year: 2022 end-page: 11 article-title: Beyond random effects: when small‐study findings are more heterogeneous publication-title: Adv Meth Pract Psychol Sci – volume: 56 start-page: 363 year: 1961 end-page: 367 article-title: Partial correlations in regression computations publication-title: J Am Stat Ass – year: 2003 – volume: 80 start-page: 1145 year: 2018 end-page: 1184 article-title: Tuition fees and university enrolment: a meta‐regression analysis publication-title: Ox Bull Econ Stat – volume: 61 start-page: 203 year: 2019 end-page: 221 article-title: What drives financial hedging? A meta‐regression analysis of corporate hedging determinants publication-title: Int Rev Fin Anal – start-page: 235 year: 1976 end-page: 251 – volume: 4 start-page: 245 year: 2007 end-page: 253 article-title: An exploratory test for an excess of significant findings publication-title: Clin Trials – volume: 14 issue: 3 year: 2023 article-title: A critical reflection on computing the sampling variance of the partial correlation coefficient publication-title: Res Synth Methods – volume: 4 start-page: 390 issue: 4 year: 2013 end-page: 405 article-title: The synthesis of partial effect sizes publication-title: J Soc Soc Work Res – volume: 8 start-page: 1 year: 2016 end-page: 32 article-title: Star wars: the empirics strike back publication-title: Am Econ J: Appl Econ – volume: 20 start-page: 293 year: 2015 end-page: 309 article-title: Meta‐analysis using effect size distributions of only statistically significant studies publication-title: Psychol Methods – volume: 34 start-page: 2116 year: 2015 end-page: 2127 article-title: Neither fixed nor random: weighted least squares meta‐analysis publication-title: Stat Med – year: 2012 – ident: e_1_2_7_7_1 doi: 10.5243/jsswr.2013.24 – ident: e_1_2_7_3_1 doi: 10.1111/obes.12240 – ident: e_1_2_7_16_1 doi: 10.1080/01621459.1961.10482120 – ident: e_1_2_7_5_1 doi: 10.1002/jrsm.1632 – ident: e_1_2_7_11_1 doi: 10.1002/jrsm.1512 – ident: e_1_2_7_4_1 doi: 10.1016/j.irfa.2018.11.006 – ident: e_1_2_7_12_1 doi: 10.3102/10769986021004299 – volume: 5 start-page: 1 year: 2022 ident: e_1_2_7_15_1 article-title: Beyond random effects: when small‐study findings are more heterogeneous publication-title: Adv Meth Pract Psychol Sci contributor: fullname: Stanley TD – ident: e_1_2_7_8_1 doi: 10.1257/app.20150044 – ident: e_1_2_7_13_1 doi: 10.1037/met0000025 – start-page: 235 volume-title: Essays in Probability and Statistics year: 1976 ident: e_1_2_7_6_1 contributor: fullname: Olkin I – ident: e_1_2_7_14_1 doi: 10.1002/sim.6481 – volume-title: Introductory Econometrics year: 2003 ident: e_1_2_7_17_1 contributor: fullname: Wooldridge JM – ident: e_1_2_7_10_1 doi: 10.1177/1740774507079441 – ident: e_1_2_7_2_1 doi: 10.4324/9780203111710 – ident: e_1_2_7_9_1 doi: 10.1093/jeea/jvac053 |
SSID | ssj0000396267 |
Score | 2.3586073 |
Snippet | Partial correlation coefficients are often used as effect sizes in the meta‐analysis and systematic review of multiple regression analysis research results.... Partial correlation coefficients are often used as effect sizes in the meta-analysis and systematic review of multiple regression analysis research results.... |
SourceID | proquest crossref pubmed eric wiley |
SourceType | Aggregation Database Index Database Publisher |
StartPage | 515 |
SubjectTerms | Bias Coefficient of variation Correlation Correlation coefficients Effect Size Error Correction Error Patterns Mathematical Formulas mean square errors Meta Analysis Meta-Analysis as Topic Multiple regression analysis partial correlation coefficients Regression (Statistics) Regression coefficients Sampling Standard error Standard error of estimate Statistical Bias Statistical Distributions Statistical tests Variance analysis |
Title | Correct standard errors can bias meta‐analysis |
URI | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fjrsm.1631 http://eric.ed.gov/ERICWebPortal/detail?accno=EJ1376273 https://www.ncbi.nlm.nih.gov/pubmed/36880162 https://www.proquest.com/docview/2809452904 https://search.proquest.com/docview/2784387465 |
Volume | 14 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8NAEB5Ke_EivqrRWqJ40ENsstlHgqdaW0qhImqht7CbbkHBVpL27k_wN_pLnM1LexC8BTIJYWZn9vs2u98AXOh5rKRwqRPElDtUEuFIaQJCZgg_aKhodjx6fM-HEzqasmkNbsqzMLk-RLXgZjIjq9cmwaVKOz-ioa9J-naNaAKpTwNhDTftCwh9qBZYXD9EsJ41VxEsdJAZhKWykEs61dMb89HmludfWHMTumZzz2AHtgvQaHfzKO9CTS_2YLdIy9S-LLSjr_bB7ZluG_HKLpcIbJ0kyyS10YO2epGp_aZX8uvjUxZiJAcwGfSfe0OnaIrgxBTTx1FeyFhskJBmVDNpGIHiWntEEhIKhCtzLaVSoeZzJRjjyKdk4EvJ_Jk3o8JvQn2xXOgjsI0yzUwhL42Vohi0wDd6eGgtkGEzn1twXromes-1L6Jc5ZhExn-R8Z8FTeO0yqA_8rBmISiyoFW6MSryIo1IgHSSkdClFpxVt3FEm98UcqGXa7QRAfUDQTmz4DB3f_V2n2O98Tix4DKLx9_fFY0en8bm4vj_piewZbrJ5_sZW1BfJWt9iphjpdrZ2GpDo3t7dztoZyz7G9G50Wo |
link.rule.ids | 220,314,780,784,11562,27924,27925,46052,46476 |
linkProvider | Wiley-Blackwell |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8NAEB6kHvQiVq3GZxQPeohNNvtIwItIS622iA_oLewmW1BoK0m9-xP8jf4SZ_PSHgRvgUxC-GZn95vJ7jcAp3ocKylc6gQx5Q6VRDhSGoeQBOkHDRXNj0cPhrz3TPsjNlqCy-osTKEPURfcTGTk87UJcFOQbv-ohr6m2eQC6QTmPsuUU2HGN6H3dYXF9UNk63l3FcFCB1ODsJIWckm7fnphQVrc8_yLbC5y13zx6a7DWska7avCzU1Y0tMNaJZxmdlnpXj0-Sa416bdRjy3qxqBrdN0lmY2QmirF5nZEz2XXx-fslQj2YLnbufpuueUXRGcmGL8OMoLGYsNFdKMaiZNSqC41h6RhIQC-cpYS6lUqPlYCcY4JlQy8KVkfuIlVPgtaExnU70DtpGmSRQmprFSFL0W-EYQD60FptjM5xacVNBEb4X4RVTIHJPI4BcZ_CxoGdBqg07fw0kLWZEF-xWMURkYWUQCzCcZCV1qwXF9G4e0-U8hp3r2jjYioH4gKGcWbBfw12_3OU44HicWnOX--Pu7ov7D48Bc7P7f9AhWek-Du-juZni7B6umtXyxuXEfGvP0XR8gAZmrw3ycfQO_2tJr |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3JSsRAEC1kBPEibqNxjeJBD9Gk00uCJ1EHHZ1hcIG5he6kBxRmIZm5-wl-o19idTadg-AtkOoQqrq63-vlFcCJHsRKCpc6QUy5QyURjpQmICRB-EFDRfPr0Z0uv3ul7T7rL8BldRem0IeoF9xMZuTjtUnwSTK4-BENfU-z4TmiCaQ-i2Zzz5QvILRXL7C4fohgPS-uIljoIDMIK2Uhl1zUrefmo_kjz7-w5jx0zeee1iqslKDRviqivAYLerQOa2VaZvZpqR19tgHutam2EU_taonA1mk6TjMbPWirN5nZQz2VXx-fshQj2YTX1u3L9Z1TFkVwYorp4ygvZCw2SEgzqpk0jEBxrT0iCQkFwpWBllKpUPOBEoxx5FMy8KVkfuIlVPhNaIzGI70NtlGmSRTy0lgpikELfKOHh9YCGTbzuQXHlWuiSaF9ERUqxyQy_ouM_yxoGqfVBrdtD8csBEUW7FVujMq8yCISIJ1kJHSpBUf1a-zRZptCjvR4hjYioH4gKGcWbBXur7_ucxxvPE4sOM3j8fd_Re2n54552Pm_6SEs9W5a0eN992EXlk1h-eJo4x40pulM7yP8mKqDvJt9A34B0Ys |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Correct+standard+errors+can+bias+meta-analysis&rft.jtitle=Research+synthesis+methods&rft.au=Stanley%2C+T+D&rft.au=Doucouliagos%2C+Hristos&rft.date=2023-05-01&rft.eissn=1759-2887&rft.volume=14&rft.issue=3&rft.spage=515&rft.epage=519&rft_id=info:doi/10.1002%2Fjrsm.1631&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1759-2879&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1759-2879&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1759-2879&client=summon |