Estimating average treatment effect using multiple imputation for handling confounder missingness
Bibliographic record
Abstract
This study presents a causal double robust estimator within the multiple imputation (MI) framework to address confounder missingness in observational studies. Three MI approaches are evaluated for estimating average treatment effects (ATE) under the missing at random mechanism. This study investigates how different imputation and missing data model specifications affect estimation under various treatment proportions and effect modification scenarios with continuous and binary outcomes. Simulation results indicate that unbiased ATE estimation requires appropriate imputation model specifications. For continuous outcomes, both outcome and treatment must be included in the imputation model, whereas for binary outcomes, either variable is sufficient for unbiased estimation. Including the outcome and treatment in the imputation model improves efficiency across all three MI approaches, particularly for continuous outcomes, without effect modification. A higher treatment proportion increases estimation efficiency for both outcome types given a specific imputation and missing data model. Under a certain imputation model, all MI approaches demonstrate greater efficiency when only the outcome model is correct in the double robust estimator, highlighting the estimator’s sensitivity to the outcome model. A real-world data application using the B-Aware trial supports simulation results that efficient effect estimation is possible when the imputation model includes both outcome and treatment.
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 | 0.040 | 0.158 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".