National HIV prevalence estimates for sub-Saharan Africa: controlling selection bias with Heckman-type selection models
- Daniel R Hogan1,2,
- Joshua A Salomon1,2,
- David Canning2,
- James K Hammitt3,4,
- Alan M Zaslavsky5,
- Till Bärnighausen2,6
- 1Center for Health Decision Science, Harvard School of Public Health, Boston, Massachusetts, USA
- 2Department of Global Health and Population, Harvard School of Public Health, Boston, Massachusetts, USA
- 3Center for Risk Analysis, Harvard University, Boston, Massachusetts, USA
- 4Toulouse School of Economics (LERNA-INRA), Toulouse, France
- 5Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts, USA
- 6Africa Centre for Health and Population Studies, University of KwaZulu-Natal, Mtubatuba, South Africa
- Correspondence to Dr Daniel R Hogan, Harvard School of Public Health, Department of Global Health and Population, 665 Huntington Ave, Building 1, Room 1104, Boston, MA 02115, USA;
UNAIDS Report 2012 Guest Editors
Peter D Ghys
Geoff P Garnett
- Accepted 18 August 2012
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.
Contributors DRH, JAS, DC, TB: conceived the study; DRH: obtained and analysed the data; DRH, JAS, DC, JKH, AMZ, TB: contributed to analytic methods and interpretation of results; DRH: wrote the first draft of the manuscript; JAS, DC, JKH, AMZ, TB: revised the manuscript before submission.
Funding DRH was supported by a Harvard University Dissertation Completion Fellowship and a T-32 Training Grant from the National Institute of Allergy and Infectious Diseases (AI 007433). DC received funding support from the William and Flora Hewlett Foundation (2008-2302 and 2011-6455) and the National Institute of Aging (5P30AG024409). TB received funding support through the National Institute of Child Health and Human Development (1R01-HD058482-01) and the National Institute of Mental Health (1R01-MH083539-01). JAS, JKH and AMZ have no financial disclosures.
Competing interests None.
Ethics approval Ethics committee approval was not required for this work. All data were analysed anonymously.
Provenance and peer review Not commissioned; externally peer reviewed.
Data sharing statement Stata code demonstrating how to implement Heckman-type selection models for imputing HIV status is available at our academic website: http://dvn.iq.harvard.edu/dvn/dv/CPDS/faces/study/StudyPage.xhtml?studyId=75001&versionNumber=2.
Open Access This is an Open Access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 3.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/3.0/
This is an open-access article distributed under the terms of the Creative Commons Attribution Non-commercial License, which permits use, distribution, and reproduction in any medium, provided the original work is properly cited, the use is non commercial and is otherwise in compliance with the license. See: http://creativecommons.org/licenses/by-nc/3.0/ and http://creativecommons.org/licenses/by-nc/3.0/legalcode