eprintid: 1476060 rev_number: 28 eprint_status: archive userid: 608 dir: disk0/01/47/60/60 datestamp: 2016-04-06 13:58:12 lastmod: 2021-10-05 00:26:44 status_changed: 2016-04-06 13:58:12 type: article metadata_visibility: show creators_name: McGovern, ME creators_name: Bärnighausen, T creators_name: Marra, G creators_name: Radice, R title: On the assumption of bivariate normality in selection models: a Copula approach applied to estimating HIV prevalence. ispublished: pub divisions: UCL divisions: B04 divisions: C06 divisions: F61 keywords: Adult, Computer Simulation, Female, HIV Infections, Humans, Male, Models, Statistical, Normal Distribution, Prevalence, Selection Bias, Zambia abstract: BACKGROUND: Heckman-type selection models have been used to control HIV prevalence estimates for selection bias when participation in HIV testing and HIV status are associated after controlling for observed variables. These models typically rely on the strong assumption that the error terms in the participation and the outcome equations that comprise the model are distributed as bivariate normal. METHODS: We introduce a novel approach for relaxing the bivariate normality assumption in selection models using copula functions. We apply this method to estimating HIV prevalence and new confidence intervals (CI) in the 2007 Zambia Demographic and Health Survey (DHS) by using interviewer identity as the selection variable that predicts participation (consent to test) but not the outcome (HIV status). RESULTS: We show in a simulation study that selection models can generate biased results when the bivariate normality assumption is violated. In the 2007 Zambia DHS, HIV prevalence estimates are similar irrespective of the structure of the association assumed between participation and outcome. For men, we estimate a population HIV prevalence of 21% (95% CI = 16%-25%) compared with 12% (11%-13%) among those who consented to be tested; for women, the corresponding figures are 19% (13%-24%) and 16% (15%-17%). CONCLUSIONS: Copula approaches to Heckman-type selection models are a useful addition to the methodological toolkit of HIV epidemiology and of epidemiology in general. We develop the use of this approach to systematically evaluate the robustness of HIV prevalence estimates based on selection models, both empirically and in a simulation study. date: 2015-03 date_type: published official_url: http://dx.doi.org/10.1097/EDE.0000000000000218 oa_status: green full_text_type: other pmcid: PMC4726739 language: eng primo: open primo_central: open_green article_type_text: Journal Article verified: verified_manual elements_id: 1021952 doi: 10.1097/EDE.0000000000000218 pii: 00001648-201503000-00016 lyricists_name: Marra, Giampiero lyricists_id: GMARR98 actors_name: Marra, Giampiero actors_name: Smith, Robert actors_id: GMARR98 actors_id: RSSMI20 actors_role: owner actors_role: impersonator full_text_status: public publication: Epidemiology volume: 26 number: 2 pagerange: 229-237 event_location: United States issn: 1531-5487 citation: McGovern, ME; Bärnighausen, T; Marra, G; Radice, R; (2015) On the assumption of bivariate normality in selection models: a Copula approach applied to estimating HIV prevalence. Epidemiology , 26 (2) pp. 229-237. 10.1097/EDE.0000000000000218 <https://doi.org/10.1097/EDE.0000000000000218>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/1476060/3/Marra_1476060_Epi%20Paper%2010%2015%2013.pdf