Le SIDA en Afrique subsaharienne (serveur d'exploration)

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

National HIV prevalence estimates for sub-Saharan Africa: controlling selection bias with Heckman-type selection models

Identifieur interne : 003578 ( Main/Exploration ); précédent : 003577; suivant : 003579

National HIV prevalence estimates for sub-Saharan Africa: controlling selection bias with Heckman-type selection models

Auteurs : Daniel R. Hogan [États-Unis] ; Joshua A. Salomon [États-Unis] ; David Canning [États-Unis] ; James K. Hammitt [États-Unis, France] ; Alan M. Zaslavsky [États-Unis] ; Till B Rnighausen [États-Unis, Afrique du Sud]

Source :

RBID : ISTEX:72CE95E1489C62E2B031E273FB0DCA69C36E950C

Descripteurs français

English descriptors

Abstract

Objectives Population-based HIV testing surveys have become central to deriving estimates of national HIV prevalence in sub-Saharan Africa. However, limited participation in these surveys can lead to selection bias. We control for selection bias in national HIV prevalence estimates using a novel approach, which unlike conventional imputation can account for selection on unobserved factors. Methods For 12 Demographic and Health Surveys conducted from 2001 to 2009 (N=138 300), we predict HIV status among those missing a valid HIV test with Heckman-type selection models, which allow for correlation between infection status and participation in survey HIV testing. We compare these estimates with conventional ones and introduce a simulation procedure that incorporates regression model parameter uncertainty into confidence intervals. Results Selection model point estimates of national HIV prevalence were greater than unadjusted estimates for 10 of 12 surveys for men and 11 of 12 surveys for women, and were also greater than the majority of estimates obtained from conventional imputation, with significantly higher HIV prevalence estimates for men in Cote d'Ivoire 2005, Mali 2006 and Zambia 2007. Accounting for selective non-participation yielded 95% confidence intervals around HIV prevalence estimates that are wider than those obtained with conventional imputation by an average factor of 4.5. Conclusions Our analysis indicates that national HIV prevalence estimates for many countries in sub-Saharan African are more uncertain than previously thought, and may be underestimated in several cases, underscoring the need for increasing participation in HIV surveys. Heckman-type selection models should be included in the set of tools used for routine estimation of HIV prevalence.

Url:
DOI: 10.1136/sextrans-2012-050636


Affiliations:


Links toward previous steps (curation, corpus...)


Le document en format XML

<record>
<TEI wicri:istexFullTextTei="biblStruct">
<teiHeader>
<fileDesc>
<titleStmt>
<title>National HIV prevalence estimates for sub-Saharan Africa: controlling selection bias with Heckman-type selection models</title>
<author>
<name sortKey="Hogan, Daniel R" sort="Hogan, Daniel R" uniqKey="Hogan D" first="Daniel R" last="Hogan">Daniel R. Hogan</name>
</author>
<author>
<name sortKey="Salomon, Joshua A" sort="Salomon, Joshua A" uniqKey="Salomon J" first="Joshua A" last="Salomon">Joshua A. Salomon</name>
</author>
<author>
<name sortKey="Canning, David" sort="Canning, David" uniqKey="Canning D" first="David" last="Canning">David Canning</name>
</author>
<author>
<name sortKey="Hammitt, James K" sort="Hammitt, James K" uniqKey="Hammitt J" first="James K" last="Hammitt">James K. Hammitt</name>
</author>
<author>
<name sortKey="Zaslavsky, Alan M" sort="Zaslavsky, Alan M" uniqKey="Zaslavsky A" first="Alan M" last="Zaslavsky">Alan M. Zaslavsky</name>
</author>
<author>
<name sortKey="B Rnighausen, Till" sort="B Rnighausen, Till" uniqKey="B Rnighausen T" first="Till" last="B Rnighausen">Till B Rnighausen</name>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:72CE95E1489C62E2B031E273FB0DCA69C36E950C</idno>
<date when="2012" year="2012">2012</date>
<idno type="doi">10.1136/sextrans-2012-050636</idno>
<idno type="url">https://api.istex.fr/document/72CE95E1489C62E2B031E273FB0DCA69C36E950C/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002540</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002540</idno>
<idno type="wicri:Area/Istex/Curation">002540</idno>
<idno type="wicri:Area/Istex/Checkpoint">000458</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000458</idno>
<idno type="wicri:doubleKey">1368-4973:2012:Hogan D:national:hiv:prevalence</idno>
<idno type="wicri:Area/Main/Merge">003603</idno>
<idno type="wicri:Area/Main/Curation">003578</idno>
<idno type="wicri:Area/Main/Exploration">003578</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title level="a">National HIV prevalence estimates for sub-Saharan Africa: controlling selection bias with Heckman-type selection models</title>
<author>
<name sortKey="Hogan, Daniel R" sort="Hogan, Daniel R" uniqKey="Hogan D" first="Daniel R" last="Hogan">Daniel R. Hogan</name>
<affiliation wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Center for Health Decision Science, Harvard School of Public Health, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
</placeName>
</affiliation>
<affiliation wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Global Health and Population, Harvard School of Public Health, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
</placeName>
</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 wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Center for Health Decision Science, Harvard School of Public Health, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
</placeName>
</affiliation>
<affiliation wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Global Health and Population, Harvard School of Public Health, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Canning, David" sort="Canning, David" uniqKey="Canning D" first="David" last="Canning">David Canning</name>
<affiliation wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Global Health and Population, Harvard School of Public Health, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Hammitt, James K" sort="Hammitt, James K" uniqKey="Hammitt J" first="James K" last="Hammitt">James K. Hammitt</name>
<affiliation wicri:level="4">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Center for Risk Analysis, Harvard University, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
<settlement type="city">Cambridge (Massachusetts)</settlement>
</placeName>
<orgName type="university">Université Harvard</orgName>
</affiliation>
<affiliation wicri:level="3">
<country xml:lang="fr">France</country>
<wicri:regionArea>Toulouse School of Economics (LERNA-INRA), Toulouse</wicri:regionArea>
<placeName>
<region type="region">Occitanie (région administrative)</region>
<region type="old region">Midi-Pyrénées</region>
<settlement type="city">Toulouse</settlement>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Zaslavsky, Alan M" sort="Zaslavsky, Alan M" uniqKey="Zaslavsky A" first="Alan M" last="Zaslavsky">Alan M. Zaslavsky</name>
<affiliation wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
</placeName>
</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 wicri:level="2">
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Global Health and Population, Harvard School of Public Health, Boston, Massachusetts</wicri:regionArea>
<placeName>
<region type="state">Massachusetts</region>
</placeName>
</affiliation>
<affiliation wicri:level="1">
<country xml:lang="fr">Afrique du Sud</country>
<wicri:regionArea>Africa Centre for Health and Population Studies, University of KwaZulu-Natal, Mtubatuba</wicri:regionArea>
<wicri:noRegion>Mtubatuba</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series>
<title level="j">Sexually Transmitted Infections</title>
<title level="j" type="abbrev">Sex Transm Infect</title>
<idno type="ISSN">1368-4973</idno>
<idno type="eISSN">1472-3263</idno>
<imprint>
<publisher>BMJ Publishing Group Ltd</publisher>
<date type="published" when="2012-12">2012-12</date>
<biblScope unit="volume">88</biblScope>
<biblScope unit="issue">Suppl 2</biblScope>
<biblScope unit="page" from="17">i17</biblScope>
</imprint>
<idno type="ISSN">1368-4973</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt>
<idno type="ISSN">1368-4973</idno>
</seriesStmt>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>Aids estimates</term>
<term>Aids relief</term>
<term>Antiretroviral treatment</term>
<term>Blood samples</term>
<term>Cape town</term>
<term>Consent regression</term>
<term>Contact regression</term>
<term>Contact regressions</term>
<term>Conventional estimates</term>
<term>Conventional imputation</term>
<term>Conventional imputation approach</term>
<term>Correlation parameter</term>
<term>Cote mali</term>
<term>Democratic republic</term>
<term>Emergency plan</term>
<term>Exclusion restriction</term>
<term>Extreme bounds</term>
<term>Final reports</term>
<term>Funding support</term>
<term>Global health</term>
<term>Global report</term>
<term>Harvard school</term>
<term>Health surveys</term>
<term>Household questionnaire</term>
<term>Imputation</term>
<term>Individual interview</term>
<term>Individual questionnaire</term>
<term>Interviewer</term>
<term>Interviewer identity</term>
<term>Large adjustment</term>
<term>Longitudinal study</term>
<term>Mali</term>
<term>Many countries</term>
<term>Modelling</term>
<term>More emphasis</term>
<term>National aids</term>
<term>National institute</term>
<term>National surveys</term>
<term>Online</term>
<term>Parametric model</term>
<term>Parametric simulation approach</term>
<term>Past year</term>
<term>Prevalence</term>
<term>Prevalence estimate</term>
<term>Prevalence estimates</term>
<term>Probit</term>
<term>Projection package</term>
<term>Public health</term>
<term>Refusal bias</term>
<term>Regression</term>
<term>Regression parameter uncertainty</term>
<term>Representative surveys</term>
<term>Sampling distribution</term>
<term>Sampling uncertainty</term>
<term>Selection bias</term>
<term>Selection equation</term>
<term>Selection model</term>
<term>Selection model approach</term>
<term>Selection model correlation parameter</term>
<term>Selection model estimates</term>
<term>Selection model point estimates</term>
<term>Selection models</term>
<term>Selection variables</term>
<term>Sensitivity analysis</term>
<term>Separate regressions</term>
<term>Several cases</term>
<term>Several countries</term>
<term>Sexual behaviour</term>
<term>Standard errors</term>
<term>Statistical analyses</term>
<term>Surveillance data</term>
<term>Survey interviewer</term>
<term>Survey reports</term>
<term>Test results</term>
<term>Testing participation</term>
<term>Testing surveys</term>
<term>Transm</term>
<term>Unaids</term>
<term>Unaids estimation</term>
<term>Unaids report</term>
<term>Unobserved factors</term>
<term>Zambia</term>
</keywords>
<keywords scheme="Teeft" xml:lang="en">
<term>Aids estimates</term>
<term>Aids relief</term>
<term>Antiretroviral treatment</term>
<term>Blood samples</term>
<term>Cape town</term>
<term>Consent regression</term>
<term>Contact regression</term>
<term>Contact regressions</term>
<term>Conventional estimates</term>
<term>Conventional imputation</term>
<term>Conventional imputation approach</term>
<term>Correlation parameter</term>
<term>Cote mali</term>
<term>Democratic republic</term>
<term>Emergency plan</term>
<term>Exclusion restriction</term>
<term>Extreme bounds</term>
<term>Final reports</term>
<term>Funding support</term>
<term>Global health</term>
<term>Global report</term>
<term>Harvard school</term>
<term>Health surveys</term>
<term>Household questionnaire</term>
<term>Imputation</term>
<term>Individual interview</term>
<term>Individual questionnaire</term>
<term>Interviewer</term>
<term>Interviewer identity</term>
<term>Large adjustment</term>
<term>Longitudinal study</term>
<term>Mali</term>
<term>Many countries</term>
<term>Modelling</term>
<term>More emphasis</term>
<term>National aids</term>
<term>National institute</term>
<term>National surveys</term>
<term>Online</term>
<term>Parametric model</term>
<term>Parametric simulation approach</term>
<term>Past year</term>
<term>Prevalence</term>
<term>Prevalence estimate</term>
<term>Prevalence estimates</term>
<term>Probit</term>
<term>Projection package</term>
<term>Public health</term>
<term>Refusal bias</term>
<term>Regression</term>
<term>Regression parameter uncertainty</term>
<term>Representative surveys</term>
<term>Sampling distribution</term>
<term>Sampling uncertainty</term>
<term>Selection bias</term>
<term>Selection equation</term>
<term>Selection model</term>
<term>Selection model approach</term>
<term>Selection model correlation parameter</term>
<term>Selection model estimates</term>
<term>Selection model point estimates</term>
<term>Selection models</term>
<term>Selection variables</term>
<term>Sensitivity analysis</term>
<term>Separate regressions</term>
<term>Several cases</term>
<term>Several countries</term>
<term>Sexual behaviour</term>
<term>Standard errors</term>
<term>Statistical analyses</term>
<term>Surveillance data</term>
<term>Survey interviewer</term>
<term>Survey reports</term>
<term>Test results</term>
<term>Testing participation</term>
<term>Testing surveys</term>
<term>Transm</term>
<term>Unaids</term>
<term>Unaids estimation</term>
<term>Unaids report</term>
<term>Unobserved factors</term>
<term>Zambia</term>
</keywords>
<keywords scheme="Wicri" type="geographic" xml:lang="fr">
<term>Mali</term>
<term>Zambie</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr">
<term>Santé publique</term>
</keywords>
</textClass>
<langUsage>
<language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front>
<div type="abstract">Objectives Population-based HIV testing surveys have become central to deriving estimates of national HIV prevalence in sub-Saharan Africa. However, limited participation in these surveys can lead to selection bias. We control for selection bias in national HIV prevalence estimates using a novel approach, which unlike conventional imputation can account for selection on unobserved factors. Methods For 12 Demographic and Health Surveys conducted from 2001 to 2009 (N=138 300), we predict HIV status among those missing a valid HIV test with Heckman-type selection models, which allow for correlation between infection status and participation in survey HIV testing. We compare these estimates with conventional ones and introduce a simulation procedure that incorporates regression model parameter uncertainty into confidence intervals. Results Selection model point estimates of national HIV prevalence were greater than unadjusted estimates for 10 of 12 surveys for men and 11 of 12 surveys for women, and were also greater than the majority of estimates obtained from conventional imputation, with significantly higher HIV prevalence estimates for men in Cote d'Ivoire 2005, Mali 2006 and Zambia 2007. Accounting for selective non-participation yielded 95% confidence intervals around HIV prevalence estimates that are wider than those obtained with conventional imputation by an average factor of 4.5. Conclusions Our analysis indicates that national HIV prevalence estimates for many countries in sub-Saharan African are more uncertain than previously thought, and may be underestimated in several cases, underscoring the need for increasing participation in HIV surveys. Heckman-type selection models should be included in the set of tools used for routine estimation of HIV prevalence.</div>
</front>
</TEI>
<affiliations>
<list>
<country>
<li>Afrique du Sud</li>
<li>France</li>
<li>États-Unis</li>
</country>
<region>
<li>Massachusetts</li>
<li>Midi-Pyrénées</li>
<li>Occitanie (région administrative)</li>
</region>
<settlement>
<li>Cambridge (Massachusetts)</li>
<li>Toulouse</li>
</settlement>
<orgName>
<li>Université Harvard</li>
</orgName>
</list>
<tree>
<country name="États-Unis">
<region name="Massachusetts">
<name sortKey="Hogan, Daniel R" sort="Hogan, Daniel R" uniqKey="Hogan D" first="Daniel R" last="Hogan">Daniel R. Hogan</name>
</region>
<name sortKey="B Rnighausen, Till" sort="B Rnighausen, Till" uniqKey="B Rnighausen T" first="Till" last="B Rnighausen">Till B Rnighausen</name>
<name sortKey="Canning, David" sort="Canning, David" uniqKey="Canning D" first="David" last="Canning">David Canning</name>
<name sortKey="Hammitt, James K" sort="Hammitt, James K" uniqKey="Hammitt J" first="James K" last="Hammitt">James K. Hammitt</name>
<name sortKey="Hogan, Daniel R" sort="Hogan, Daniel R" uniqKey="Hogan D" first="Daniel R" last="Hogan">Daniel R. Hogan</name>
<name sortKey="Salomon, Joshua A" sort="Salomon, Joshua A" uniqKey="Salomon J" first="Joshua A" last="Salomon">Joshua A. Salomon</name>
<name sortKey="Salomon, Joshua A" sort="Salomon, Joshua A" uniqKey="Salomon J" first="Joshua A" last="Salomon">Joshua A. Salomon</name>
<name sortKey="Zaslavsky, Alan M" sort="Zaslavsky, Alan M" uniqKey="Zaslavsky A" first="Alan M" last="Zaslavsky">Alan M. Zaslavsky</name>
</country>
<country name="France">
<region name="Occitanie (région administrative)">
<name sortKey="Hammitt, James K" sort="Hammitt, James K" uniqKey="Hammitt J" first="James K" last="Hammitt">James K. Hammitt</name>
</region>
</country>
<country name="Afrique du Sud">
<noRegion>
<name sortKey="B Rnighausen, Till" sort="B Rnighausen, Till" uniqKey="B Rnighausen T" first="Till" last="B Rnighausen">Till B Rnighausen</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/SidaSubSaharaV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003578 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 003578 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Sante
   |area=    SidaSubSaharaV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     ISTEX:72CE95E1489C62E2B031E273FB0DCA69C36E950C
   |texte=   National HIV prevalence estimates for sub-Saharan Africa: controlling selection bias with Heckman-type selection models
}}

Wicri

This area was generated with Dilib version V0.6.32.
Data generation: Mon Nov 13 19:31:10 2017. Site generation: Wed Mar 6 19:14:32 2024