A Bayesian framework to account for misclassification error and uncertainty in the estimation of abortion incidence
Bibliographic record
Abstract
Obtaining reliable estimates of the incidence of induced abortion remains a significant challenge in abortion re- search. In recent years, one indirect, survey-based technique for measuring the incidence of induced abortion which has gained significant attention is the Confidante Method. The method has been employed in various legal and social contexts, however, its efficacy has not been uniformly established and many studies have found its success to be context-dependent. Greater focus has been placed recently on assessing the method’s key assumptions and quantifying and adjusting for biases that arise from violations in those assumptions. In this paper we propose a general statistical framework to conceptualize and quantify the impact of biases on measuring abortion incidence from surveys. Specifically, we define the relationship between observed and true abortion prevalence based on misclassification error related to the sensitivity and specificity of the survey instrument. We argue that this formulation leads naturally to a Bayesian modeling approach to estimate abortion prevalence. Such a modelling framework allows for different levels of uncertainty about the misclassification parameters to be incorporated in the modeling process, with that uncertainty being propagated through to the final estimates. We illustrate our framework and modelling approach on data from an application of the Confidante Method in Uganda in 2018, where we account for systematic differences in confidante abortion reports based on the self-reported abortion experiences of surveyed individuals.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.049 | 0.115 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.003 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.006 | 0.003 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".