Original title: Bayesian Statistical Modeling in Action for Estimation and Forecasting in Low- and Middle-income Countries: The Case of the Family Planning Estimation Tool
Leontine Alkema, Herbert Susmann, Evan Ray, S.J. Mooney +11 · September 2026
Low- and middle-income countries need to track family planning, but accurate data can be hard to get. Researchers use a system called the Family Planning Estimation Tool, or FPET, to estimate and forecast rates of modern contraceptive use and unmet contraceptive need. It works by fitting a Bayesian statistical model to country-specific survey data and service statistics, combining these sources while accounting for errors. Over the past decade, user feedback has helped improve the tool. The authors updated the model to better capture contraceptive transitions, handle error-prone survey data, and incorporate service statistics. By running a validation exercise, they found that FPET is reasonably well calibrated. They also share broader lessons and challenges for tracking global health indicators.
Imagine you are trying to guess how many people in a town own a bicycle. You have a few old surveys and some bike shop sales records, but both are incomplete and sometimes wrong. In this paper, the researchers use a smart method that combines these imperfect sources and accounts for changes over time to give a reliable estimate.
Accurate estimates of contraceptive use help governments and health organizations allocate resources effectively. In low- and middle-income countries, where survey data is often sparse or unreliable, this tool provides crucial insights for family planning programs. Better forecasts mean better planning for health services, ultimately improving women's health and autonomy.
The model is only as good as the data it uses; in settings with very few surveys, estimates may be uncertain. The validation exercise showed reasonable calibration but not perfect accuracy. The paper does not cover all possible indicators or countries. The model relies on assumptions about how contraceptive use changes over time.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Bayesian Statistical Modeling in Action for Estimation and Forecasting in Low- and Middle-income Countries: The Case of the Family Planning Estimation Tool — Leontine Alkema, Herbert Susmann, Evan Ray et al. — Statistics and Public Policy — doi:10.1080/2330443x.2026.2735367
Abstract licence: CC BY
Explanation generated by Synthesis from the abstract — it is not the original paper.