Reducing Treatment Selection Bias for Estimating Treatment Effects Using Propensity Score Method
Bibliographic record
Abstract
Treatment selection bias leads to an inaccurate estimation of treatment effects as applied to specific sites or problem locations. Treatment selection bias is a major source of inconsistency in the results obtained from conventional before and after and cross-sectional models. One of the major expressions of treatment selection bias concerns the use of collision occurrence data in justifying intervention. For example, in highway safety field, a treatment is often introduced at a given site based on its high collision experience. Under normal conditions we would expect these collision numbers to return to a lower long term expected value, regardless of intervention. For treated sites, conventional observational models ascribe this reduction in collisions to the given treatment. This results in an overestimation of treatment effect. In this paper, a propensity score model is introduced that deals explicitly with treatment selection bias. The model is applied to Canadian highway–railway grade crossings data to estimate reductions in collision subject to upgrades in warning devices. The results of the propensity score model are compared for similar types of treatments to a number of before and after and cross-sectional models for both U.S. and Canadian data. The propensity score method is shown to reduce treatment selection bias and has probable merit that need to be further examined.
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 | 0.122 | 0.310 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.005 | 0.007 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.010 | 0.002 |
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".