Prediction intervals for random-effects meta-analysis: A confidence distribution approach

Prediction intervals are commonly used in meta-analysis with random-effects models. One widely used method, the Higgins–Thompson–Spiegelhalter prediction interval, replaces the heterogeneity parameter with its point estimate, but its validity strongly depends on a large sample approximation. This is...

Full description

Saved in:
Bibliographic Details
Published in:Statistical methods in medical research 2019-06, Vol.28 (6), p.1689-1702
Main Authors: Nagashima, Kengo, Noma, Hisashi, Furukawa, Toshi A
Format: Article
Language:English
Subjects:
Computer simulation
Intervals
Meta-analysis
Parameter estimation
Strength
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-c473t-a9a596a65c64dde245ee5f5a5ba9516e75e72f2c0b3daa5049d35345df2dee0d3
cites cdi_FETCH-LOGICAL-c473t-a9a596a65c64dde245ee5f5a5ba9516e75e72f2c0b3daa5049d35345df2dee0d3
container_end_page 1702
container_issue 6
container_start_page 1689
container_title Statistical methods in medical research
container_volume 28
creator Nagashima, Kengo
Noma, Hisashi
Furukawa, Toshi A
description Prediction intervals are commonly used in meta-analysis with random-effects models. One widely used method, the Higgins–Thompson–Spiegelhalter prediction interval, replaces the heterogeneity parameter with its point estimate, but its validity strongly depends on a large sample approximation. This is a weakness in meta-analyses with few studies. We propose an alternative based on bootstrap and show by simulations that its coverage is close to the nominal level, unlike the Higgins–Thompson–Spiegelhalter method and its extensions. The proposed method was applied in three meta-analyses.
doi_str_mv 10.1177/0962280218773520
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2037051218</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sage_id>10.1177_0962280218773520</sage_id><sourcerecordid>2239142980</sourcerecordid><originalsourceid>FETCH-LOGICAL-c473t-a9a596a65c64dde245ee5f5a5ba9516e75e72f2c0b3daa5049d35345df2dee0d3</originalsourceid><addsrcrecordid>eNp1kLtLBDEQh4Mo3vnorWTBxmY1z83FTg5fIGihhdUyl0w0crt7JruC_70571QQrKaYb76Z-RFywOgJY1qfUlNxPqGcTbQWitMNMmZS65IKITfJeNkul_0R2UnplVKqqTTbZMSNloqbakye7iO6YPvQtUVoe4zvME-F72IRoXVdU6L3aPtUNNhDCS3MP1JIZ8V5YbvWB4etxcKF1McwG74ssFjEDuzLHtny2YX767pLHi8vHqbX5e3d1c30_La0Uou-BAPKVFApW0nnkEuFqLwCNQOjWIVaoeaeWzoTDkDl-51QQirnuUOkTuyS45U3r30bMPV1E5LF-Rxa7IZUcyo0VSxnlNGjP-hrN8T8U6a4MExyM6GZoivKxi6liL5exNBA_KgZrZex139jzyOHa_Ewa9D9DHznnIFyBSR4xt-t_wo_AdG0imU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2239142980</pqid></control><display><type>article</type><title>Prediction intervals for random-effects meta-analysis: A confidence distribution approach</title><source>Applied Social Sciences Index &amp; Abstracts (ASSIA)</source><source>SAGE</source><creator>Nagashima, Kengo ; Noma, Hisashi ; Furukawa, Toshi A</creator><creatorcontrib>Nagashima, Kengo ; Noma, Hisashi ; Furukawa, Toshi A</creatorcontrib><description>Prediction intervals are commonly used in meta-analysis with random-effects models. One widely used method, the Higgins–Thompson–Spiegelhalter prediction interval, replaces the heterogeneity parameter with its point estimate, but its validity strongly depends on a large sample approximation. This is a weakness in meta-analyses with few studies. We propose an alternative based on bootstrap and show by simulations that its coverage is close to the nominal level, unlike the Higgins–Thompson–Spiegelhalter method and its extensions. The proposed method was applied in three meta-analyses.</description><identifier>ISSN: 0962-2802</identifier><identifier>EISSN: 1477-0334</identifier><identifier>DOI: 10.1177/0962280218773520</identifier><identifier>PMID: 29745296</identifier><language>eng</language><publisher>London, England: SAGE Publications</publisher><subject>Computer simulation ; Intervals ; Meta-analysis ; Parameter estimation ; Strength</subject><ispartof>Statistical methods in medical research, 2019-06, Vol.28 (6), p.1689-1702</ispartof><rights>The Author(s) 2018</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c473t-a9a596a65c64dde245ee5f5a5ba9516e75e72f2c0b3daa5049d35345df2dee0d3</citedby><cites>FETCH-LOGICAL-c473t-a9a596a65c64dde245ee5f5a5ba9516e75e72f2c0b3daa5049d35345df2dee0d3</cites><orcidid>0000-0003-4529-9045 ; 0000-0002-2520-9949</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925,30999,79364</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29745296$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Nagashima, Kengo</creatorcontrib><creatorcontrib>Noma, Hisashi</creatorcontrib><creatorcontrib>Furukawa, Toshi A</creatorcontrib><title>Prediction intervals for random-effects meta-analysis: A confidence distribution approach</title><title>Statistical methods in medical research</title><addtitle>Stat Methods Med Res</addtitle><description>Prediction intervals are commonly used in meta-analysis with random-effects models. One widely used method, the Higgins–Thompson–Spiegelhalter prediction interval, replaces the heterogeneity parameter with its point estimate, but its validity strongly depends on a large sample approximation. This is a weakness in meta-analyses with few studies. We propose an alternative based on bootstrap and show by simulations that its coverage is close to the nominal level, unlike the Higgins–Thompson–Spiegelhalter method and its extensions. The proposed method was applied in three meta-analyses.</description><subject>Computer simulation</subject><subject>Intervals</subject><subject>Meta-analysis</subject><subject>Parameter estimation</subject><subject>Strength</subject><issn>0962-2802</issn><issn>1477-0334</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>7QJ</sourceid><recordid>eNp1kLtLBDEQh4Mo3vnorWTBxmY1z83FTg5fIGihhdUyl0w0crt7JruC_70571QQrKaYb76Z-RFywOgJY1qfUlNxPqGcTbQWitMNMmZS65IKITfJeNkul_0R2UnplVKqqTTbZMSNloqbakye7iO6YPvQtUVoe4zvME-F72IRoXVdU6L3aPtUNNhDCS3MP1JIZ8V5YbvWB4etxcKF1McwG74ssFjEDuzLHtny2YX767pLHi8vHqbX5e3d1c30_La0Uou-BAPKVFApW0nnkEuFqLwCNQOjWIVaoeaeWzoTDkDl-51QQirnuUOkTuyS45U3r30bMPV1E5LF-Rxa7IZUcyo0VSxnlNGjP-hrN8T8U6a4MExyM6GZoivKxi6liL5exNBA_KgZrZex139jzyOHa_Ewa9D9DHznnIFyBSR4xt-t_wo_AdG0imU</recordid><startdate>20190601</startdate><enddate>20190601</enddate><creator>Nagashima, Kengo</creator><creator>Noma, Hisashi</creator><creator>Furukawa, Toshi A</creator><general>SAGE Publications</general><general>Sage Publications Ltd</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QJ</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>K9.</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0003-4529-9045</orcidid><orcidid>https://orcid.org/0000-0002-2520-9949</orcidid></search><sort><creationdate>20190601</creationdate><title>Prediction intervals for random-effects meta-analysis: A confidence distribution approach</title><author>Nagashima, Kengo ; Noma, Hisashi ; Furukawa, Toshi A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c473t-a9a596a65c64dde245ee5f5a5ba9516e75e72f2c0b3daa5049d35345df2dee0d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer simulation</topic><topic>Intervals</topic><topic>Meta-analysis</topic><topic>Parameter estimation</topic><topic>Strength</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nagashima, Kengo</creatorcontrib><creatorcontrib>Noma, Hisashi</creatorcontrib><creatorcontrib>Furukawa, Toshi A</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Applied Social Sciences Index &amp; Abstracts (ASSIA)</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>Statistical methods in medical research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nagashima, Kengo</au><au>Noma, Hisashi</au><au>Furukawa, Toshi A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prediction intervals for random-effects meta-analysis: A confidence distribution approach</atitle><jtitle>Statistical methods in medical research</jtitle><addtitle>Stat Methods Med Res</addtitle><date>2019-06-01</date><risdate>2019</risdate><volume>28</volume><issue>6</issue><spage>1689</spage><epage>1702</epage><pages>1689-1702</pages><issn>0962-2802</issn><eissn>1477-0334</eissn><abstract>Prediction intervals are commonly used in meta-analysis with random-effects models. One widely used method, the Higgins–Thompson–Spiegelhalter prediction interval, replaces the heterogeneity parameter with its point estimate, but its validity strongly depends on a large sample approximation. This is a weakness in meta-analyses with few studies. We propose an alternative based on bootstrap and show by simulations that its coverage is close to the nominal level, unlike the Higgins–Thompson–Spiegelhalter method and its extensions. The proposed method was applied in three meta-analyses.</abstract><cop>London, England</cop><pub>SAGE Publications</pub><pmid>29745296</pmid><doi>10.1177/0962280218773520</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0003-4529-9045</orcidid><orcidid>https://orcid.org/0000-0002-2520-9949</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0962-2802
ispartof Statistical methods in medical research, 2019-06, Vol.28 (6), p.1689-1702
issn 0962-2802
1477-0334
language eng
recordid cdi_proquest_miscellaneous_2037051218
source Applied Social Sciences Index & Abstracts (ASSIA); SAGE
subjects Computer simulation
Intervals
Meta-analysis
Parameter estimation
Strength
title Prediction intervals for random-effects meta-analysis: A confidence distribution approach
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T06%3A13%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prediction%20intervals%20for%20random-effects%20meta-analysis:%20A%20confidence%20distribution%20approach&rft.jtitle=Statistical%20methods%20in%20medical%20research&rft.au=Nagashima,%20Kengo&rft.date=2019-06-01&rft.volume=28&rft.issue=6&rft.spage=1689&rft.epage=1702&rft.pages=1689-1702&rft.issn=0962-2802&rft.eissn=1477-0334&rft_id=info:doi/10.1177/0962280218773520&rft_dat=%3Cproquest_cross%3E2239142980%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c473t-a9a596a65c64dde245ee5f5a5ba9516e75e72f2c0b3daa5049d35345df2dee0d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2239142980&rft_id=info:pmid/29745296&rft_sage_id=10.1177_0962280218773520&rfr_iscdi=true