Using interviewer random effects to remove selection bias from HIV prevalence estimates.
Identifieur interne : 000297 ( PubMed/Corpus ); précédent : 000296; suivant : 000298Using interviewer random effects to remove selection bias from HIV prevalence estimates.
Auteurs : Mark E. Mcgovern ; Till B Rnighausen ; Joshua A. Salomon ; David CanningSource :
- BMC medical research methodology [ 1471-2288 ] ; 2015.
English descriptors
- KwdEn :
- Adolescent, Adult, Algorithms, Ghana (epidemiology), HIV Infections (diagnosis), HIV Infections (epidemiology), Health Surveys (methods), Health Surveys (statistics & numerical data), Humans, Interviews as Topic (methods), Mass Screening (methods), Mass Screening (statistics & numerical data), Middle Aged, Models, Statistical, Prevalence, Selection Bias, Young Adult, Zambia (epidemiology).
- MESH :
- geographic , epidemiology : Ghana, Zambia.
- diagnosis : HIV Infections.
- epidemiology : HIV Infections.
- methods : Health Surveys, Interviews as Topic, Mass Screening.
- statistics & numerical data : Health Surveys, Mass Screening.
- Adolescent, Adult, Algorithms, Humans, Middle Aged, Models, Statistical, Prevalence, Selection Bias, Young Adult.
Abstract
Selection bias in HIV prevalence estimates occurs if non-participation in testing is correlated with HIV status. Longitudinal data suggests that individuals who know or suspect they are HIV positive are less likely to participate in testing in HIV surveys, in which case methods to correct for missing data which are based on imputation and observed characteristics will produce biased results.
DOI: 10.1186/1471-2288-15-8
PubMed: 25656226
Links to Exploration step
pubmed:25656226Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Using interviewer random effects to remove selection bias from HIV prevalence estimates.</title><author><name sortKey="Mcgovern, Mark E" sort="Mcgovern, Mark E" uniqKey="Mcgovern M" first="Mark E" last="Mcgovern">Mark E. Mcgovern</name><affiliation><nlm:affiliation>Harvard Center for Population and Development Studies, 9 Bow Street, Cambridge, MA, 02138, USA. mcgovern@hsph.harvard.edu.</nlm:affiliation></affiliation></author><author><name sortKey="B Rnighausen, Till" sort="B Rnighausen, Till" uniqKey="B Rnighausen T" first="Till" last="B Rnighausen">Till B Rnighausen</name><affiliation><nlm:affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. tbaernig@hsph.harvard.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Salomon, Joshua A" sort="Salomon, Joshua A" uniqKey="Salomon J" first="Joshua A" last="Salomon">Joshua A. Salomon</name><affiliation><nlm:affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. jsalomon@hsph.harvard.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Canning, David" sort="Canning, David" uniqKey="Canning D" first="David" last="Canning">David Canning</name><affiliation><nlm:affiliation>Harvard Center for Population and Development Studies, 9 Bow Street, Cambridge, MA, 02138, USA. dcanning@hsph.harvard.edu.</nlm:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2015">2015</date><idno type="RBID">pubmed:25656226</idno><idno type="pmid">25656226</idno><idno type="doi">10.1186/1471-2288-15-8</idno><idno type="wicri:Area/PubMed/Corpus">000297</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000297</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Using interviewer random effects to remove selection bias from HIV prevalence estimates.</title><author><name sortKey="Mcgovern, Mark E" sort="Mcgovern, Mark E" uniqKey="Mcgovern M" first="Mark E" last="Mcgovern">Mark E. Mcgovern</name><affiliation><nlm:affiliation>Harvard Center for Population and Development Studies, 9 Bow Street, Cambridge, MA, 02138, USA. mcgovern@hsph.harvard.edu.</nlm:affiliation></affiliation></author><author><name sortKey="B Rnighausen, Till" sort="B Rnighausen, Till" uniqKey="B Rnighausen T" first="Till" last="B Rnighausen">Till B Rnighausen</name><affiliation><nlm:affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. tbaernig@hsph.harvard.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Salomon, Joshua A" sort="Salomon, Joshua A" uniqKey="Salomon J" first="Joshua A" last="Salomon">Joshua A. Salomon</name><affiliation><nlm:affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. jsalomon@hsph.harvard.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Canning, David" sort="Canning, David" uniqKey="Canning D" first="David" last="Canning">David Canning</name><affiliation><nlm:affiliation>Harvard Center for Population and Development Studies, 9 Bow Street, Cambridge, MA, 02138, USA. dcanning@hsph.harvard.edu.</nlm:affiliation></affiliation></author></analytic><series><title level="j">BMC medical research methodology</title><idno type="eISSN">1471-2288</idno><imprint><date when="2015" type="published">2015</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adolescent</term><term>Adult</term><term>Algorithms</term><term>Ghana (epidemiology)</term><term>HIV Infections (diagnosis)</term><term>HIV Infections (epidemiology)</term><term>Health Surveys (methods)</term><term>Health Surveys (statistics & numerical data)</term><term>Humans</term><term>Interviews as Topic (methods)</term><term>Mass Screening (methods)</term><term>Mass Screening (statistics & numerical data)</term><term>Middle Aged</term><term>Models, Statistical</term><term>Prevalence</term><term>Selection Bias</term><term>Young Adult</term><term>Zambia (epidemiology)</term></keywords><keywords scheme="MESH" type="geographic" qualifier="epidemiology" xml:lang="en"><term>Ghana</term><term>Zambia</term></keywords><keywords scheme="MESH" qualifier="diagnosis" xml:lang="en"><term>HIV Infections</term></keywords><keywords scheme="MESH" qualifier="epidemiology" xml:lang="en"><term>HIV Infections</term></keywords><keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Health Surveys</term><term>Interviews as Topic</term><term>Mass Screening</term></keywords><keywords scheme="MESH" qualifier="statistics & numerical data" xml:lang="en"><term>Health Surveys</term><term>Mass Screening</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Adolescent</term><term>Adult</term><term>Algorithms</term><term>Humans</term><term>Middle Aged</term><term>Models, Statistical</term><term>Prevalence</term><term>Selection Bias</term><term>Young Adult</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Selection bias in HIV prevalence estimates occurs if non-participation in testing is correlated with HIV status. Longitudinal data suggests that individuals who know or suspect they are HIV positive are less likely to participate in testing in HIV surveys, in which case methods to correct for missing data which are based on imputation and observed characteristics will produce biased results.</div></front></TEI><pubmed><MedlineCitation Status="MEDLINE" Owner="NLM"><PMID Version="1">25656226</PMID><DateCreated><Year>2015</Year><Month>05</Month><Day>15</Day></DateCreated><DateCompleted><Year>2016</Year><Month>03</Month><Day>14</Day></DateCompleted><DateRevised><Year>2017</Year><Month>09</Month><Day>02</Day></DateRevised><Article PubModel="Electronic"><Journal><ISSN IssnType="Electronic">1471-2288</ISSN><JournalIssue CitedMedium="Internet"><Volume>15</Volume><PubDate><Year>2015</Year><Month>Feb</Month><Day>05</Day></PubDate></JournalIssue><Title>BMC medical research methodology</Title><ISOAbbreviation>BMC Med Res Methodol</ISOAbbreviation></Journal><ArticleTitle>Using interviewer random effects to remove selection bias from HIV prevalence estimates.</ArticleTitle><Pagination><MedlinePgn>8</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.1186/1471-2288-15-8</ELocationID><Abstract><AbstractText Label="BACKGROUND" NlmCategory="BACKGROUND">Selection bias in HIV prevalence estimates occurs if non-participation in testing is correlated with HIV status. Longitudinal data suggests that individuals who know or suspect they are HIV positive are less likely to participate in testing in HIV surveys, in which case methods to correct for missing data which are based on imputation and observed characteristics will produce biased results.</AbstractText><AbstractText Label="METHODS" NlmCategory="METHODS">The identity of the HIV survey interviewer is typically associated with HIV testing participation, but is unlikely to be correlated with HIV status. Interviewer identity can thus be used as a selection variable allowing estimation of Heckman-type selection models. These models produce asymptotically unbiased HIV prevalence estimates, even when non-participation is correlated with unobserved characteristics, such as knowledge of HIV status. We introduce a new random effects method to these selection models which overcomes non-convergence caused by collinearity, small sample bias, and incorrect inference in existing approaches. Our method is easy to implement in standard statistical software, and allows the construction of bootstrapped standard errors which adjust for the fact that the relationship between testing and HIV status is uncertain and needs to be estimated.</AbstractText><AbstractText Label="RESULTS" NlmCategory="RESULTS">Using nationally representative data from the Demographic and Health Surveys, we illustrate our approach with new point estimates and confidence intervals (CI) for HIV prevalence among men in Ghana (2003) and Zambia (2007). In Ghana, we find little evidence of selection bias as our selection model gives an HIV prevalence estimate of 1.4% (95% CI 1.2% - 1.6%), compared to 1.6% among those with a valid HIV test. In Zambia, our selection model gives an HIV prevalence estimate of 16.3% (95% CI 11.0% - 18.4%), compared to 12.1% among those with a valid HIV test. Therefore, those who decline to test in Zambia are found to be more likely to be HIV positive.</AbstractText><AbstractText Label="CONCLUSIONS" NlmCategory="CONCLUSIONS">Our approach corrects for selection bias in HIV prevalence estimates, is possible to implement even when HIV prevalence or non-participation is very high or very low, and provides a practical solution to account for both sampling and parameter uncertainty in the estimation of confidence intervals. The wide confidence intervals estimated in an example with high HIV prevalence indicate that it is difficult to correct statistically for the bias that may occur when a large proportion of people refuse to test.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>McGovern</LastName><ForeName>Mark E</ForeName><Initials>ME</Initials><AffiliationInfo><Affiliation>Harvard Center for Population and Development Studies, 9 Bow Street, Cambridge, MA, 02138, USA. mcgovern@hsph.harvard.edu.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. mcgovern@hsph.harvard.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Bärnighausen</LastName><ForeName>Till</ForeName><Initials>T</Initials><AffiliationInfo><Affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. tbaernig@hsph.harvard.edu.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>Wellcome Trust Africa Centre for Health and Population Studies, University of KwaZulu-Natal, Mtubatuba, South Africa. tbaernig@hsph.harvard.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Salomon</LastName><ForeName>Joshua A</ForeName><Initials>JA</Initials><AffiliationInfo><Affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. jsalomon@hsph.harvard.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Canning</LastName><ForeName>David</ForeName><Initials>D</Initials><AffiliationInfo><Affiliation>Harvard Center for Population and Development Studies, 9 Bow Street, Cambridge, MA, 02138, USA. dcanning@hsph.harvard.edu.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA. dcanning@hsph.harvard.edu.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><GrantList CompleteYN="Y"><Grant><GrantID>WT097410</GrantID><Agency>Wellcome Trust</Agency><Country>United Kingdom</Country></Grant><Grant><GrantID>P30 AG024409</GrantID><Acronym>AG</Acronym><Agency>NIA NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>R01 HD084233</GrantID><Acronym>HD</Acronym><Agency>NICHD NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>1 P30 AG024409-09</GrantID><Acronym>AG</Acronym><Agency>NIA NIH HHS</Agency><Country>United States</Country></Grant><Grant><Agency>Wellcome Trust</Agency><Country>United Kingdom</Country></Grant></GrantList><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType><PublicationType UI="D052061">Research Support, N.I.H., Extramural</PublicationType><PublicationType UI="D013485">Research Support, Non-U.S. Gov't</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2015</Year><Month>02</Month><Day>05</Day></ArticleDate></Article><MedlineJournalInfo><Country>England</Country><MedlineTA>BMC Med Res Methodol</MedlineTA><NlmUniqueID>100968545</NlmUniqueID><ISSNLinking>1471-2288</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><CommentsCorrectionsList><CommentsCorrections RefType="Cites"><RefSource>PLoS One. 2010;5(8):e12370</RefSource><PMID Version="1">20811499</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Lancet. 2003 Dec 6;362(9399):1929-31</RefSource><PMID Version="1">14667753</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Bull World Health Organ. 2006 Jul;84(7):537-45</RefSource><PMID Version="1">16878227</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Emerg Themes Epidemiol. 2013 Feb 27;10(1):2</RefSource><PMID Version="1">23446064</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>AIDS. 2009 Mar 13;23(5):621-9</RefSource><PMID Version="1">19182677</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>J Health Econ. 2008 Mar;27(2):300-7</RefSource><PMID Version="1">18180064</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>AIDS. 2013 Jan 14;27(2):233-42</RefSource><PMID Version="1">22842993</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Sex Transm Infect. 2012 Dec;88 Suppl 2:i17-23</RefSource><PMID Version="1">23172342</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Sex Transm Infect. 2008 Aug;84 Suppl 1:i63-i70</RefSource><PMID Version="1">18647869</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>PLoS One. 2014;9(11):e112563</RefSource><PMID Version="1">25402333</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Int J Epidemiol. 2012 Dec;41(6):1602-13</RefSource><PMID Version="1">23148108</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Biostatistics. 2000 Mar;1(1):113-22</RefSource><PMID Version="1">12933529</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Demography. 2014 Jun;51(3):1131-57</RefSource><PMID Version="1">24788481</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Epidemiology. 2011 Jan;22(1):27-35</RefSource><PMID Version="1">21150352</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Trop Med Int Health. 2012 Aug;17(8):e103-10</RefSource><PMID Version="1">22943374</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>BMC Public Health. 2009;9:163</RefSource><PMID Version="1">19476618</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Sex Transm Infect. 2008 Aug;84 Suppl 1:i71-i77</RefSource><PMID Version="1">18647870</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Demography. 2010 Aug;47(3):651-65</RefSource><PMID Version="1">20879682</PMID></CommentsCorrections></CommentsCorrectionsList><MeshHeadingList><MeshHeading><DescriptorName UI="D000293" MajorTopicYN="N">Adolescent</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D000328" MajorTopicYN="N">Adult</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D000465" MajorTopicYN="N">Algorithms</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D005869" MajorTopicYN="N" Type="Geographic">Ghana</DescriptorName><QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D015658" MajorTopicYN="N">HIV Infections</DescriptorName><QualifierName UI="Q000175" MajorTopicYN="Y">diagnosis</QualifierName><QualifierName UI="Q000453" MajorTopicYN="Y">epidemiology</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D006306" MajorTopicYN="N">Health Surveys</DescriptorName><QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName><QualifierName UI="Q000706" MajorTopicYN="N">statistics & numerical data</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D007407" MajorTopicYN="N">Interviews as Topic</DescriptorName><QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D008403" MajorTopicYN="N">Mass Screening</DescriptorName><QualifierName UI="Q000379" MajorTopicYN="N">methods</QualifierName><QualifierName UI="Q000706" MajorTopicYN="N">statistics & numerical data</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D008875" MajorTopicYN="N">Middle Aged</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D015233" MajorTopicYN="N">Models, Statistical</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D015995" MajorTopicYN="N">Prevalence</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D015983" MajorTopicYN="N">Selection Bias</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D055815" MajorTopicYN="N">Young Adult</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D015024" MajorTopicYN="N" Type="Geographic">Zambia</DescriptorName><QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName></MeshHeading></MeshHeadingList><OtherID Source="NLM">PMC4429465</OtherID></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2014</Year><Month>07</Month><Day>09</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2015</Year><Month>01</Month><Day>06</Day></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2015</Year><Month>2</Month><Day>7</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2015</Year><Month>2</Month><Day>7</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2016</Year><Month>3</Month><Day>15</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>epublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">25656226</ArticleId><ArticleId IdType="doi">10.1186/1471-2288-15-8</ArticleId><ArticleId IdType="pii">1471-2288-15-8</ArticleId><ArticleId IdType="pmc">PMC4429465</ArticleId></ArticleIdList></PubmedData></pubmed></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/SidaGhanaV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000297 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000297 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Sante
|area= SidaGhanaV1
|flux= PubMed
|étape= Corpus
|type= RBID
|clé= pubmed:25656226
|texte= Using interviewer random effects to remove selection bias from HIV prevalence estimates.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:25656226" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a SidaGhanaV1
| This area was generated with Dilib version V0.6.31. |  |