Accounting for nonsampling error in estimates of HIV epidemic trends from antenatal clinic sentinel surveillance

Jeffrey W. Eaton, Le Bao

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Objectives: The aim of the study was to propose and demonstrate an approach to allow additional nonsampling uncertainty about HIV prevalence measured at antenatal clinic sentinel surveillance (ANC-SS) in model-based inferences about trends in HIV incidence and prevalence. Design: Mathematical model fitted to surveillance data with Bayesian inference. Methods: We introduce a variance inflation parameter that accounts for the uncertainty of nonsampling errors in ANC-SS prevalence. It is additive to the sampling error variance. Three approaches are tested for estimating using ANC-SS and household survey data from 40 subnational regions in nine countries in sub-Saharan, as defined in UNAIDS 2016 estimates. Methods were compared using in-sample fit and out-of-sample prediction of ANC-SS data, fit to household survey prevalence data, and the computational implications. Results: Introducing the additional variance parameter increased the error variance around ANC-SS prevalence observations by a median of 2.7 times (interquartile range 1.9-3.8). Using only sampling error in ANC-SS prevalence, coverage of 95% prediction intervals was 69% in out-of-sample prediction tests. This increased to 90% after introducing the additional variance parameter. The revised probabilistic model improved model fit to household survey prevalence and increased epidemic uncertainty intervals most during the early epidemic period before 2005. Estimating did not increase the computational cost of model fitting. Conclusions: We recommend estimating nonsampling error in ANC-SS as an additional parameter in Bayesian inference using the Estimation and Projection Package model. This approach may prove useful for incorporating other data sources such as routine prevalence from Prevention of mother-to-child transmission testing into future epidemic estimates.

Original languageEnglish (US)
Pages (from-to)S61-S68
JournalAIDS
Volume31
DOIs
StatePublished - Apr 1 2017

Fingerprint

Sentinel Surveillance
HIV
Uncertainty
Selection Bias
Information Storage and Retrieval
Economic Inflation
Statistical Models
Theoretical Models
Mothers
Costs and Cost Analysis

All Science Journal Classification (ASJC) codes

  • Immunology and Allergy
  • Immunology
  • Infectious Diseases

Cite this

@article{e86ecd3c04414f17af789878add095fa,
title = "Accounting for nonsampling error in estimates of HIV epidemic trends from antenatal clinic sentinel surveillance",
abstract = "Objectives: The aim of the study was to propose and demonstrate an approach to allow additional nonsampling uncertainty about HIV prevalence measured at antenatal clinic sentinel surveillance (ANC-SS) in model-based inferences about trends in HIV incidence and prevalence. Design: Mathematical model fitted to surveillance data with Bayesian inference. Methods: We introduce a variance inflation parameter that accounts for the uncertainty of nonsampling errors in ANC-SS prevalence. It is additive to the sampling error variance. Three approaches are tested for estimating using ANC-SS and household survey data from 40 subnational regions in nine countries in sub-Saharan, as defined in UNAIDS 2016 estimates. Methods were compared using in-sample fit and out-of-sample prediction of ANC-SS data, fit to household survey prevalence data, and the computational implications. Results: Introducing the additional variance parameter increased the error variance around ANC-SS prevalence observations by a median of 2.7 times (interquartile range 1.9-3.8). Using only sampling error in ANC-SS prevalence, coverage of 95{\%} prediction intervals was 69{\%} in out-of-sample prediction tests. This increased to 90{\%} after introducing the additional variance parameter. The revised probabilistic model improved model fit to household survey prevalence and increased epidemic uncertainty intervals most during the early epidemic period before 2005. Estimating did not increase the computational cost of model fitting. Conclusions: We recommend estimating nonsampling error in ANC-SS as an additional parameter in Bayesian inference using the Estimation and Projection Package model. This approach may prove useful for incorporating other data sources such as routine prevalence from Prevention of mother-to-child transmission testing into future epidemic estimates.",
author = "Eaton, {Jeffrey W.} and Le Bao",
year = "2017",
month = "4",
day = "1",
doi = "10.1097/QAD.0000000000001419",
language = "English (US)",
volume = "31",
pages = "S61--S68",
journal = "AIDS",
issn = "0269-9370",
publisher = "Lippincott Williams and Wilkins",

}

Accounting for nonsampling error in estimates of HIV epidemic trends from antenatal clinic sentinel surveillance. / Eaton, Jeffrey W.; Bao, Le.

In: AIDS, Vol. 31, 01.04.2017, p. S61-S68.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Accounting for nonsampling error in estimates of HIV epidemic trends from antenatal clinic sentinel surveillance

AU - Eaton, Jeffrey W.

AU - Bao, Le

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Objectives: The aim of the study was to propose and demonstrate an approach to allow additional nonsampling uncertainty about HIV prevalence measured at antenatal clinic sentinel surveillance (ANC-SS) in model-based inferences about trends in HIV incidence and prevalence. Design: Mathematical model fitted to surveillance data with Bayesian inference. Methods: We introduce a variance inflation parameter that accounts for the uncertainty of nonsampling errors in ANC-SS prevalence. It is additive to the sampling error variance. Three approaches are tested for estimating using ANC-SS and household survey data from 40 subnational regions in nine countries in sub-Saharan, as defined in UNAIDS 2016 estimates. Methods were compared using in-sample fit and out-of-sample prediction of ANC-SS data, fit to household survey prevalence data, and the computational implications. Results: Introducing the additional variance parameter increased the error variance around ANC-SS prevalence observations by a median of 2.7 times (interquartile range 1.9-3.8). Using only sampling error in ANC-SS prevalence, coverage of 95% prediction intervals was 69% in out-of-sample prediction tests. This increased to 90% after introducing the additional variance parameter. The revised probabilistic model improved model fit to household survey prevalence and increased epidemic uncertainty intervals most during the early epidemic period before 2005. Estimating did not increase the computational cost of model fitting. Conclusions: We recommend estimating nonsampling error in ANC-SS as an additional parameter in Bayesian inference using the Estimation and Projection Package model. This approach may prove useful for incorporating other data sources such as routine prevalence from Prevention of mother-to-child transmission testing into future epidemic estimates.

AB - Objectives: The aim of the study was to propose and demonstrate an approach to allow additional nonsampling uncertainty about HIV prevalence measured at antenatal clinic sentinel surveillance (ANC-SS) in model-based inferences about trends in HIV incidence and prevalence. Design: Mathematical model fitted to surveillance data with Bayesian inference. Methods: We introduce a variance inflation parameter that accounts for the uncertainty of nonsampling errors in ANC-SS prevalence. It is additive to the sampling error variance. Three approaches are tested for estimating using ANC-SS and household survey data from 40 subnational regions in nine countries in sub-Saharan, as defined in UNAIDS 2016 estimates. Methods were compared using in-sample fit and out-of-sample prediction of ANC-SS data, fit to household survey prevalence data, and the computational implications. Results: Introducing the additional variance parameter increased the error variance around ANC-SS prevalence observations by a median of 2.7 times (interquartile range 1.9-3.8). Using only sampling error in ANC-SS prevalence, coverage of 95% prediction intervals was 69% in out-of-sample prediction tests. This increased to 90% after introducing the additional variance parameter. The revised probabilistic model improved model fit to household survey prevalence and increased epidemic uncertainty intervals most during the early epidemic period before 2005. Estimating did not increase the computational cost of model fitting. Conclusions: We recommend estimating nonsampling error in ANC-SS as an additional parameter in Bayesian inference using the Estimation and Projection Package model. This approach may prove useful for incorporating other data sources such as routine prevalence from Prevention of mother-to-child transmission testing into future epidemic estimates.

UR - http://www.scopus.com/inward/record.url?scp=85016016690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016016690&partnerID=8YFLogxK

U2 - 10.1097/QAD.0000000000001419

DO - 10.1097/QAD.0000000000001419

M3 - Article

C2 - 28296801

AN - SCOPUS:85016016690

VL - 31

SP - S61-S68

JO - AIDS

JF - AIDS

SN - 0269-9370

ER -