Back

A subnational family planning estimation tool (SFPET) for estimating contraceptive use and unmet need by subnational areas and demographic subgroups

Kong, D.; Claps, E.; Kirkman, C.; Enriquez, M.; Ressler, B.; Mercer, L.; Buxton, S.; Izzo, M.; Proctor, J. L.

2022-12-14 public and global health
10.1101/2022.12.12.22283357 medRxiv
Show abstract

BackgroundAccess to safe, effective, and voluntary family planning (FP) is a fundamental human right and is an important step toward achieving gender equality and economic autonomy. Global organizations have set ambitious goals to create universal access to FP services but assessing progress can be challenging, especially at the local geographic scale. Here, we present a quantitative visualization tool called the subnational family planning estimation tool (SFPET) that can be used by policy makers to monitor programmatic success at subnational levels and gain insight into trends within demographic subgroups. MethodsThe visualization tool builds on the statistical methods and analyses presented in earlier research to generate model-based estimates of FP indicators for 25 sub-Saharan countries at administrative units one and two. Here, we have extended this modeling approach to more demographic and geographic subgroups, integrated recently released survey data, and constructed a web-based dashboard to navigate survey and model-based estimates. FindingsSignificant heterogeneity in the levels and trends of FP indicators exist at subnational levels and across demographic subgroups. This tool provides the ability to efficiently navigate these model-based estimates across local regions within countries and across demographic subgroups. The tool also helps highlight regions and groups that may be falling behind the national trends as well as identify exemplars that exceed the national average. InterpretationSFPET1 is an interactive dashboard created to aid policymakers in assessing progress towards family planning goals by visualizing both model-based and direct survey estimates of family planning indicators at the subnational level. This framework provides insight into locations and population segments experiencing the greatest unmet need, enabling targeting and allocation of resources to achieve family planning goals.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.