arXiv subjects

Leontine Alkema

Publications and source records attributed to Leontine Alkema.

At least 19 recordsLinked to original sources

arXiv2026

Principal Stratification with Bayesian Additive Regression Trees for Count-Valued Intermediate Variables: Estimating the Effect of Fertility on Women's Employment

Estimating the causal effect of fertility on women's employment is challenging because fertility and labour-market decisions are jointly determined. Instrumental-variable strategies are widely used, but credible instruments are rare and their validity often depends on covariates. Two-stage least squares, the dominant implementation, does not flexibly accommodate covariate-dependent instrument validity and is poorly suited to count-valued treatment and effect heterogeneity more broadly. We extend an existing framework that combines principal stratification with Bayesian Additive Regression Trees (BART) to settings with count-valued intermediate variables, such as number of children. The approach defines a causal estimand that respects the count structure of the intermediate variable, while BART enables flexible, covariate-dependent modelling of principal strata and outcomes, accommodating covariate-dependent instrument validity and producing estimates of effect heterogeneity. Simulations demonstrate that our approach outperforms conventional and flexible instrumental-variable estimators under nonlinear confounding and heterogeneous treatment effects. Applied to Demographic and Health Survey data from Nigeria, Senegal, and Kenya, the approach suggests a negative average effect in Nigeria but no clear average effect elsewhere, with employment penalties concentrated among younger, less-educated women, heterogeneity that standard approaches would obscure. The approach is available in the R package PrinceBART.

stat.ME↗

arXiv2026

Combining BART and Principal Stratification to estimate the effect of intermediate on primary outcomes with application to estimating the effect of family planning on employment in sub-Saharan Africa

There is interest in learning about the causal effect of family planning (FP) on empowerment related outcomes. Experimental data related to this question are available from trials in which FP programs increase access to FP. While program assignment is unconfounded, FP uptake and subsequent empowerment may share common causes. We use principal stratification to estimate the causal effect of an intermediate FP outcome on a primary outcome of interest, among women affected by a FP program. Within strata defined by the potential reaction to the program, FP uptake is unconfounded. To minimize the need for parametric assumptions, we propose to use Bayesian Additive Regression Trees (BART) for modeling stratum membership and outcomes of interest. We refer to the combined approach as Prince BART. We evaluate Prince BART through a simulation study and use it to assess the causal effect of modern contraceptive use on employment in six cities in Nigeria, based on quasi-experimental data from a FP program trial during the first half of the 2010s. We show that findings differ between Prince BART and alternative modeling approaches based on parametric assumptions.

stat.ME↗

arXiv2026

Combining BART and Principal Stratification to estimate the effect of intermediate variables on primary outcomes with application to estimating the effect of family planning on employment in Nigeria and Senegal

There is interest in learning about the causal effects of modern contraceptive use on empowerment outcomes. Data on this question often come from family planning (FP) programs that increase access to FP and facilitate contraceptive use among some women, rather than directly assigning use. Women whose contraceptive behavior changes because of these programs ("compliers") may differ from target populations in ways that alter the consequences of contraceptive use for empowerment outcomes. We propose a two-step approach. First, we use principal stratification and Bayesian Additive Regression Trees (BART) to estimate the effect of modern contraceptive use among compliers in the study population, treating the FP program as an instrument rather than as the treatment of interest. Second, we generalize these complier-specific effects to a broader population by averaging conditional effects over the covariate distribution in the target population, with uncertainty in that distribution quantified via a Bayesian bootstrap applied to external complex survey data. We examine performance in simulation designs previously used to evaluate IV estimators. We then apply the approach to employment among urban women in Nigeria and Senegal, finding strong and heterogeneous effects of contraceptive use. Sensitivity analyses suggest robustness to violations of assumptions for internal and external validity.

stat.ME↗

arXiv2025

Bayesian Statistical Modeling in Action for Estimation and Forecasting in Low- and Middle-income Countries: The Case of the Family Planning Estimation Tool

The Family Planning Estimation Tool (FPET) is used in low- and middle-income countries to produce estimates and short-term forecasts of family planning indicators, such as modern contraceptive use and unmet need for contraceptives. Estimates are obtained via a Bayesian statistical model that is fitted to country-specific data from surveys and service statistics data. The model has evolved over the last decade based on user inputs. In this paper we summarize the main features of the statistical model used in FPET and introduce recent updates related to capturing contraceptive transitions, fitting to survey data that may be error prone, and the use of service statistics data. We assess model performance through a validation exercise and find that FPET is reasonably well calibrated. We use our experience with FPET to briefly discuss lessons learned and open challenges related to the broader field of statistical modeling for monitoring of demographic and global health indicators.

stat.AP↗

arXiv2025

Bayesian probabilistic projections of proportions with limited data: An application to subnational contraceptive method supply shares

Engaging the private sector in contraceptive method supply is critical for creating equitable, sustainable, and accessible healthcare systems. To achieve this, it is essential to understand where women obtain their modern contraceptives. While national-level estimates provide valuable insights into overall trends in contraceptive supply, they often obscure variation within and across subnational regions. Addressing localized needs has become increasingly important as countries adopt decentralized models for family planning services. Decentralization has also underscored the need for reliable subnational estimates of key family planning indicators. The absence of regularly collected subnational data has hindered effective monitoring and decision-making. To bridge this gap, we propose a novel approach that leverages latent attributes in Demographic and Health Survey (DHS) data to produce Bayesian probabilistic projections of contraceptive method supply shares (the proportions of modern contraceptive methods supplied by public and private sectors) with limited data. Our modeling framework is built on Bayesian hierarchical models. Using penalized splines to track public and private supply shares over time, we leverage the spatial nature of the data and incorporate a correlation structure between recent supply share observations at national and subnational levels. This framework contributes to the domain of subnational estimation of proportions in data-sparse settings, outperforming comparable and previous approaches. As decentralization continues to reshape family planning services, producing reliable subnational estimates of key indicators is increasingly vital for researchers and policymakers.

stat.ME↗

arXiv2025

Flexible Modeling of Demographic Transition Processes with a Bayesian Hierarchical B-splines Model

Several demographic and health indicators, including the total fertility rate (TFR) and modern contraceptive use rate (mCPR), evolve similarly over time, characterized by a transition between stable states. Existing approaches for estimation or projection of transitions in multiple populations have successfully used parametric functions to capture the relation between the rate of change of an indicator and its level. However, incorrect parametric forms may result in bias or incorrect coverage in long-term projections. We propose a new class of models to capture demographic transitions in multiple populations. Our proposal, the B-spline Transition Model (BTM), models the relationship between the rate of change of an indicator and its level using B-splines, allowing for data-adaptive estimation of transition functions. Bayesian hierarchical models are used to share information on the transition function between populations. We apply the BTM to estimate and project country-level TFR and mCPR and compare the results against those from extant parametric models. For TFR, BTM projections have generally lower error than the comparison model. For mCPR, while results are comparable between BTM and a parametric approach, the B-spline model generally improves out-of-sample predictions. The case studies suggest that the BTM may be considered for demographic applications.

stat.ME↗

arXiv2025

Enhancing the use of family planning service statistics using a Bayesian modelling approach to inform estimates of modern contraceptive use in low- and middle-income countries

Monitoring family planning indicators, such as modern contraceptive prevalence rate (mCPR), is essential for family planning programming. The Family Planning Estimation Tool (FPET) uses survey data to estimate and forecast family planning indicators, including mCPR, over time. However, sole reliance on large-scale surveys, carried out on average every 3-5 years, can lead to data gaps. Service statistics are a readily available data source, routinely collected in conjunction with service delivery. Various service statistics data types can be used to derive a family planning indicator called Estimated Modern Use (EMU). In a number of countries, annual rates of change in EMU have been found to be predictive of true rates of change in mCPR. However, it has been challenging to capture the varying levels of uncertainty associated with the EMU indicator across different countries and service statistics data types and to subsequently quantify this uncertainty when using EMU in FPET. We present a new approach to using EMUs in FPET to inform mCPR estimates, using annual EMU rates of change as input, and accounting for uncertainty associated with the EMU derivation process. The approach also considers additional country-type-specific uncertainty. We assess the EMU type-specific uncertainty at the country level, via a Bayesian hierarchical modelling approach. Validation results and anonymised country-level case studies highlight improved predictive performance and provide insights into the impact of including EMU data on mCPR estimates compared to using survey data alone. Together, they demonstrate that EMUs can help countries monitor progress toward their family planning goals more effectively.

stat.AP↗

arXiv2024

Temporal Models for Demographic and Global Health Outcomes in Multiple Populations: Introducing the Normal-with-Optional-Shrinkage Data Model Class

Statistical models are used to produce estimates of demographic and global health indicators in populations with limited data. Such models integrate multiple data sources to produce estimates and forecasts with uncertainty based on model assumptions. Model assumptions can be divided into assumptions that describe latent trends in the indicator of interest versus assumptions on the data generating process of the observed data, conditional on the latent process value. Focusing on the latter, we introduce a class of data models that can be used to combine data from multiple sources with various reporting issues. The proposed data model accounts for sampling errors and differences in observational uncertainty based on survey characteristics. In addition, the data model employs horseshoe priors to produce estimates that are robust to outlying observations. We refer to the data model class as the normal-with-optional-shrinkage (NOS) set up. We illustrate the use of the NOS data model for the estimation of modern contraceptive use and other family planning indicators at the national level for countries globally, using survey data.

stat.ME↗

arXiv2024

Flexibly Modeling Shocks to Demographic and Health Indicators with Bayesian Shrinkage Priors

Demographic and health indicators may exhibit short or large short-term shocks; for example, armed conflicts, epidemics, or famines may cause shocks in period measures of life expectancy. Statistical models for estimating historical trends and generating future projections of these indicators for a large number of populations may be biased or not well probabilistically calibrated if they do not account for the presence of shocks. We propose a flexible method for modeling shocks when producing estimates and projections for multiple populations. The proposed approach makes no assumptions about the shape or duration of a shock, and requires no prior knowledge of when shocks may have occurred. Our approach is based on the modeling of shocks in level of the indicator of interest. We use Bayesian shrinkage priors such that shock terms are shrunk to zero unless the data suggest otherwise. The method is demonstrated in a model for male period life expectancy at birth. We use as a starting point an existing projection model and expand it by including the shock terms, modeled by the Bayesian shrinkage priors. Out-of-sample validation exercises find that including shocks in the model results in sharper uncertainty intervals without sacrificing empirical coverage or prediction error.

stat.ME↗

arXiv2023

Interview with Adrian Raftery

Professor Adrian E. Raftery is the Boeing International Professor of Statistics and Sociology, and an adjunct professor of Atmospheric Sciences, at the University of Washington in Seattle. He was born in Dublin, Ireland, and obtained a B.A. in Mathematics and an M.Sc. in Statistics and Operations Research at Trinity College Dublin. He obtained a doctorate in mathematical statistics from the Université Pierre et Marie Curie under the supervision of Paul Deheuvels. He was a lecturer in statistics at Trinity College Dublin, and then an associate and full professor of statistics and sociology at the University of Washington. He was the founding Director of the Center for Statistics and Social Sciences. Professor Raftery has published over 200 articles in peer-reviewed statistical, sociological and other journals. His research focuses on Bayesian model selection and Bayesian model averaging, model-based clustering, inference for deterministic models, and the development of new statistical methods for demography, sociology, and the environmental and health sciences. He is a member of the United States National Academy of Sciences, a Fellow of the American Academy of Arts and Sciences, an Honorary Member of the Royal Irish Academy, a member of the Washington State Academy of Sciences, a Fellow of the American Statistical Association, a Fellow of the Institute of Mathematical Statistics, and an elected Member of the Sociological Research Association. He has won multiple awards for his research. He was Coordinating and Applications Editor of the Journal of the American Statistical Association and Editor of Sociological Methodology. He was identified as the world's most cited researcher in mathematics for the period 1995-2005. Thirty-three students have obtained Ph.D.'s working under Raftery's supervision, of whom 21 hold or have held tenure-track university faculty positions.

stat.OT↗

arXiv2023

A Bayesian analysis of current duration data with reporting issues: an application to estimating the distribution of time-between-sex from time-since-last-sex data as collected in cross-sectional surveys in low- and middle-income countries

Aggregate measures of family planning are used to monitor demand for and usage of contraceptive methods in populations globally, for example as part of the FP2030 initiative. Family planning measures for low- and middle-income countries are typically based on data collected through cross-sectional household surveys. Recently proposed measures account for sexual activity through assessment of the distribution of time-between-sex (TBS) in the population of interest. In this paper, we propose a statistical approach to estimate the distribution of TBS using data typically available in low- and middle-income countries, while addressing two major challenges. The first challenge is that timing of sex information is typically limited to women's time-since-last-sex (TSLS) data collected in the cross-sectional survey. In our proposed approach, we adopt the current duration method to estimate the distribution of TBS using the available TSLS data, from which the frequency of sex at the population level can be derived. Furthermore, the observed TSLS data are subject to reporting issues because they can be reported in different units and may be rounded off. To apply the current duration approach and account for these data reporting issues, we develop a flexible Bayesian model, and provide a detailed technical description of the proposed modeling approach.

stat.AP↗

arXiv2022

Estimating the proportion of modern contraceptives supplied by the public and private sectors using a Bayesian hierarchical penalized spline model

Quantifying the public/private sector supply of contraceptive methods within countries is vital for effective and sustainable family planning (FP) delivery. In many low and middle-income countries (LMIC), measuring the contraceptive supply source often relies on Demographic Health Surveys (DHS). However, many of these countries carry out the DHS approximately every 3-5 years and do not have recent data beyond 2015/16. Our objective in estimating the set of related contraceptive supply-share outcomes (proportion of modern contraceptive methods supplied by the public/private sectors) is to take advantage of latent attributes present in dataset to produce annual, country-specific estimates and projections with uncertainty. We propose a Bayesian, hierarchical, penalized-spline model with multivariate-normal spline coefficients to capture cross-method correlations. Our approach offers an intuitive way to share information across countries and sub-continents, model the changes in the contraceptive supply share over time, account for survey observational errors and produce probabilistic estimates and projections that are informed by past changes in the contraceptive supply share as well as correlations between rates of change across different methods. These results will provide valuable information for evaluating FP program effectiveness. To the best of our knowledge, it is the first model of its kind to estimate these quantities.

stat.ME↗

arXiv2021

Temporal models for demographic and global health outcomes in multiple populations: Introducing a new framework to review and standardize documentation of model assumptions and facilitate model comparison

There is growing interest in producing estimates of demographic and global health indicators in populations with limited data. Statistical models are needed to combine data from multiple data sources into estimates and projections with uncertainty. Diverse modeling approaches have been applied to this problem, making comparisons between models difficult. We propose a model class, Temporal Models for Multiple Populations (TMMPs), to facilitate documentation of model assumptions in a standardized way and comparison across models. The class distinguishes between latent trends and the observed data, which may be noisy or exhibit systematic biases. We provide general formulations of the process model, which describes the latent trend of the indicator of interest. We show how existing models for a variety of indicators can be written as TMMPs and how the TMMP-based description can be used to compare and contrast model assumptions. We end with a discussion of outstanding questions and future directions.

stat.ME↗

arXiv2021

A Bayesian cohort component projection model to estimate adult populations at the subnational level in data-sparse settings

Accurate estimates of subnational populations are important for policy formulation and monitoring population health indicators. For example, estimates of the number of women of reproductive age are important to understand the population at risk to maternal mortality and unmet need for contraception. However, in many low-income countries, data on population counts and components of population change are limited, and so levels and trends subnationally are unclear. We present a Bayesian constrained cohort component model for the estimation and projection of subnational populations. The model builds on a cohort component projection framework, incorporates census data and estimates from the United Nation's World Population Prospects, and uses characteristic mortality schedules to obtain estimates of population counts and the components of population change, including internal migration. The data required as inputs to the model are minimal and available across a wide range of countries, including most low-income countries. The model is applied to estimate and project populations by county in Kenya for 1979-2019, and validated against the 2019 Kenyan census.

stat.AP↗

arXiv2020

Global estimation and scenario-based projections of sex ratio at birth and missing female births using a Bayesian hierarchical time series mixture model

The sex ratio at birth (SRB) is defined as the ratio of male to female live births. The SRB imbalance in parts of the world over the past several decades is a direct consequence of sex-selective abortion, driven by the co-existence of son preference, readily available technology of prenatal sex determination, and fertility decline. Estimation and projection of the degree of SRB imbalance is complicated because of variability in SRB reference levels and because of the uncertainty associated with SRB observations. We develop Bayesian hierarchical time series mixture models for SRB estimation and scenario-based projections for all countries from 1950 to 2100. We model the SRB regional and national reference levels, and the fluctuation around national reference levels. We identify countries at risk of SRB imbalances and model both (i) the absence or presence of sex ratio transitions in such countries and, if present, (ii) the transition process. The transition model of SRB imbalance captures three stages (increase, stagnation and convergence back to SRB baselines). The model identifies countries with statistical evidence of SRB inflation in a fully Bayesian approach. The scenario-based SRB projections are based on the sex ratio transition model with varying assumptions regarding the occurrence of a sex ratio transition in at-risk countries. Projections are used to quantify the future burden of missing female births due to sex-selective abortions under different scenarios.

stat.AP↗

arXiv2020

Estimating the Stillbirth Rate for 195 Countries Using A Bayesian Sparse Regression Model with Temporal Smoothing

Estimation of stillbirth rates globally is complicated because of the paucity of reliable data from countries where most stillbirths occur. We compiled data and developed a Bayesian hierarchical temporal sparse regression model for estimating stillbirth rates for all countries from 2000 to 2019. The model combines covariates with a temporal smoothing process so that estimates are data-driven in country-periods with high-quality data and deter-mined by covariates for country-periods with limited or no data. Horseshoepriors are used to encourage sparseness. The model adjusts observations with alternative stillbirth definitions and accounts for bias in observations that are subject to non-sampling errors. In-sample goodness of fit and out-of-sample validation results suggest that the model is reasonably well calibrated. The model is used by the UN Inter-agency Group for Child Mortality Estimation to monitor the stillbirth rate for all countries.

stat.AP↗

arXiv2020

Global estimation of unintended pregnancy and abortion using a Bayesian hierarchical random walk model

Unintended pregnancy and abortion estimates are needed to inform and motivate investment in global health programmes and policies. Variability in the availability and reliability of data poses challenges for producing estimates. We developed a Bayesian model that simultaneously estimates incidence of unintended pregnancy and abortion for 195 countries and territories. Our modelling strategy was informed by the proximate determinants of fertility with (i) incidence of unintended pregnancy defined by the number of women (grouped by marital and contraceptive use status) and their respective pregnancy rates, and (ii) abortion incidence defined by group-specific pregnancies and propensities to have an abortion. Hierarchical random walk models are used to estimate country-group-period-specific pregnancy rates and propensities to abort.

stat.AP↗

arXiv2019

Estimating maternal mortality using data from national civil registration vital statistics systems: A Bayesian hierarchical bivariate random walk model to estimate sensitivity and specificity of reporting

Civil registration vital statistics (CRVS) data are used to produce national estimates of maternal mortality, but are often subject to substantial reporting errors due to misclassification of maternal deaths. The accuracy of CRVS systems can be assessed by comparing CRVS-based counts of maternal and non-maternal deaths to those obtained from specialized studies, which are rigorous assessments of maternal mortality for a given country-period. We developed a Bayesian bivariate random walk model to estimate sensitivity and specificity of the reporting on maternal mortality in CRVS data, and associated CRVS adjustment factors. The model was fitted to a global data set of CRVS and specialized study data. Validation exercises suggest that the model performs well in terms of predicting CRVS-based proportions of maternal deaths for country-periods without specialized studies. The new model is used by the UN Maternal Mortality Inter-Agency Group to account for misclassification errors when estimating maternal mortality using CRVS data.

stat.AP↗