A bayesian approach to the global estimation of maternal mortality

Leontine Alkema, Sanqian Zhang, Doris Chou, Alison Gemmill, Ann Beth Moller, Doris Ma Fat, Lale Say, Colin Mathers, Daniel Hogan

Research output: Contribution to journalArticle

Abstract

The maternal mortality ratio (MMR) is defined as the number of maternal deaths in a population per 100,000 live births. Country-specific MMR estimates are published on a regular basis by the United Nations Maternal Mortality Estimation Inter-agency Group (UN MMEIG) to track progress in reducing maternal deaths and were used to evaluate regional and national performance related to Millennium Development Goal (MDG) 5, which called for a 75% reduction in the MMR between 1990 and 2015. Until 2014, the UN MMEIG used a multilevel regression model for producing estimates for countries without sufficient data from vital registration systems. While this model worked well in the past to assess MMR levels for countries with limited data, it was deemed unsatisfactory for final MDG 5 reporting for countries where longer time series of observations had become available because, by construction, estimated trends in the MMR were covariate-driven only and did not necessarily track data-driven trends. We developed a Bayesian maternal mortality estimation model, which extends upon the UN MMEIG multilevel regression model. The new model assesses data-driven trends through the inclusion of an ARIMA time series model that captures accelerations and decelerations in the rate of change in the MMR. Varying reporting and data quality issues are accounted for in source-specific data models. The revised model provides data-driven estimates of MMR levels and trends and was used for MDG 5 reporting for all countries.

Original languageEnglish (US)
Pages (from-to)1245-1274
Number of pages30
JournalAnnals of Applied Statistics
Volume11
Issue number3
DOIs
StatePublished - Sep 1 2017
Externally publishedYes

Fingerprint

Bayesian Approach
Mortality
Data-driven
Time series
Multilevel Models
Deceleration
Regression Model
Maternal mortality
Bayesian approach
Estimate
Data structures
ARIMA Models
Rate of change
Data Quality
Time Series Models
Model
Data Model
Registration
Covariates
Inclusion

Keywords

  • ARIMA time series models
  • Bayesian inference
  • Maternal mortality ratio
  • Millennium development goal 5
  • Multilevel regression model
  • UN maternal mortality estimation inter-agency group (UN MMEIG)

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty

Cite this

Alkema, L., Zhang, S., Chou, D., Gemmill, A., Moller, A. B., Fat, D. M., ... Hogan, D. (2017). A bayesian approach to the global estimation of maternal mortality. Annals of Applied Statistics, 11(3), 1245-1274. https://doi.org/10.1214/16-AOAS1014

A bayesian approach to the global estimation of maternal mortality. / Alkema, Leontine; Zhang, Sanqian; Chou, Doris; Gemmill, Alison; Moller, Ann Beth; Fat, Doris Ma; Say, Lale; Mathers, Colin; Hogan, Daniel.

In: Annals of Applied Statistics, Vol. 11, No. 3, 01.09.2017, p. 1245-1274.

Research output: Contribution to journalArticle

Alkema, L, Zhang, S, Chou, D, Gemmill, A, Moller, AB, Fat, DM, Say, L, Mathers, C & Hogan, D 2017, 'A bayesian approach to the global estimation of maternal mortality', Annals of Applied Statistics, vol. 11, no. 3, pp. 1245-1274. https://doi.org/10.1214/16-AOAS1014
Alkema, Leontine ; Zhang, Sanqian ; Chou, Doris ; Gemmill, Alison ; Moller, Ann Beth ; Fat, Doris Ma ; Say, Lale ; Mathers, Colin ; Hogan, Daniel. / A bayesian approach to the global estimation of maternal mortality. In: Annals of Applied Statistics. 2017 ; Vol. 11, No. 3. pp. 1245-1274.
@article{33efc3edc465489e86846c93451b8b95,
title = "A bayesian approach to the global estimation of maternal mortality",
abstract = "The maternal mortality ratio (MMR) is defined as the number of maternal deaths in a population per 100,000 live births. Country-specific MMR estimates are published on a regular basis by the United Nations Maternal Mortality Estimation Inter-agency Group (UN MMEIG) to track progress in reducing maternal deaths and were used to evaluate regional and national performance related to Millennium Development Goal (MDG) 5, which called for a 75{\%} reduction in the MMR between 1990 and 2015. Until 2014, the UN MMEIG used a multilevel regression model for producing estimates for countries without sufficient data from vital registration systems. While this model worked well in the past to assess MMR levels for countries with limited data, it was deemed unsatisfactory for final MDG 5 reporting for countries where longer time series of observations had become available because, by construction, estimated trends in the MMR were covariate-driven only and did not necessarily track data-driven trends. We developed a Bayesian maternal mortality estimation model, which extends upon the UN MMEIG multilevel regression model. The new model assesses data-driven trends through the inclusion of an ARIMA time series model that captures accelerations and decelerations in the rate of change in the MMR. Varying reporting and data quality issues are accounted for in source-specific data models. The revised model provides data-driven estimates of MMR levels and trends and was used for MDG 5 reporting for all countries.",
keywords = "ARIMA time series models, Bayesian inference, Maternal mortality ratio, Millennium development goal 5, Multilevel regression model, UN maternal mortality estimation inter-agency group (UN MMEIG)",
author = "Leontine Alkema and Sanqian Zhang and Doris Chou and Alison Gemmill and Moller, {Ann Beth} and Fat, {Doris Ma} and Lale Say and Colin Mathers and Daniel Hogan",
year = "2017",
month = "9",
day = "1",
doi = "10.1214/16-AOAS1014",
language = "English (US)",
volume = "11",
pages = "1245--1274",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "3",

}

TY - JOUR

T1 - A bayesian approach to the global estimation of maternal mortality

AU - Alkema, Leontine

AU - Zhang, Sanqian

AU - Chou, Doris

AU - Gemmill, Alison

AU - Moller, Ann Beth

AU - Fat, Doris Ma

AU - Say, Lale

AU - Mathers, Colin

AU - Hogan, Daniel

PY - 2017/9/1

Y1 - 2017/9/1

N2 - The maternal mortality ratio (MMR) is defined as the number of maternal deaths in a population per 100,000 live births. Country-specific MMR estimates are published on a regular basis by the United Nations Maternal Mortality Estimation Inter-agency Group (UN MMEIG) to track progress in reducing maternal deaths and were used to evaluate regional and national performance related to Millennium Development Goal (MDG) 5, which called for a 75% reduction in the MMR between 1990 and 2015. Until 2014, the UN MMEIG used a multilevel regression model for producing estimates for countries without sufficient data from vital registration systems. While this model worked well in the past to assess MMR levels for countries with limited data, it was deemed unsatisfactory for final MDG 5 reporting for countries where longer time series of observations had become available because, by construction, estimated trends in the MMR were covariate-driven only and did not necessarily track data-driven trends. We developed a Bayesian maternal mortality estimation model, which extends upon the UN MMEIG multilevel regression model. The new model assesses data-driven trends through the inclusion of an ARIMA time series model that captures accelerations and decelerations in the rate of change in the MMR. Varying reporting and data quality issues are accounted for in source-specific data models. The revised model provides data-driven estimates of MMR levels and trends and was used for MDG 5 reporting for all countries.

AB - The maternal mortality ratio (MMR) is defined as the number of maternal deaths in a population per 100,000 live births. Country-specific MMR estimates are published on a regular basis by the United Nations Maternal Mortality Estimation Inter-agency Group (UN MMEIG) to track progress in reducing maternal deaths and were used to evaluate regional and national performance related to Millennium Development Goal (MDG) 5, which called for a 75% reduction in the MMR between 1990 and 2015. Until 2014, the UN MMEIG used a multilevel regression model for producing estimates for countries without sufficient data from vital registration systems. While this model worked well in the past to assess MMR levels for countries with limited data, it was deemed unsatisfactory for final MDG 5 reporting for countries where longer time series of observations had become available because, by construction, estimated trends in the MMR were covariate-driven only and did not necessarily track data-driven trends. We developed a Bayesian maternal mortality estimation model, which extends upon the UN MMEIG multilevel regression model. The new model assesses data-driven trends through the inclusion of an ARIMA time series model that captures accelerations and decelerations in the rate of change in the MMR. Varying reporting and data quality issues are accounted for in source-specific data models. The revised model provides data-driven estimates of MMR levels and trends and was used for MDG 5 reporting for all countries.

KW - ARIMA time series models

KW - Bayesian inference

KW - Maternal mortality ratio

KW - Millennium development goal 5

KW - Multilevel regression model

KW - UN maternal mortality estimation inter-agency group (UN MMEIG)

UR - http://www.scopus.com/inward/record.url?scp=85031501922&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031501922&partnerID=8YFLogxK

U2 - 10.1214/16-AOAS1014

DO - 10.1214/16-AOAS1014

M3 - Article

AN - SCOPUS:85031501922

VL - 11

SP - 1245

EP - 1274

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 3

ER -