Exploration Of Theoretical And Application Issues In Using Fully Bayesian Methods For Road Safety Analysis
Bibliographic record
Abstract
The Fully Bayesian (FB) approach to road safety analysis has been available for some time, but it is largely unevaluated and untested. This study is trying to bridge the gap by conducting a thorough evaluation of FB method for black spots identification and treatment effect analysis. First, an evaluation is conducted on the univariate FB versus the empirical Bayesian (EB) method for single level severity data through the development of various models, and multivariate FB versus univariate FB for multilevel severity data, as well as the performance of various ranking and evaluation criteria for black spots identification. It is confirmed that the FB method is superior to the EB with respect to key ranking criteria (expected rank, mode rank and median rank of posterior PM, etc.). The multivariate FB method is better than univariate FB for the multilevel severity crashes. Then a teat of the FB before-after method for treatment effect analysis is performed. Two FB testing frameworks were employed. First the univariate before-after fully Bayesian (FB) method was examined using three simulated datasets. Then multivariate Poisson log normal (MVPLN), univariate Poisson log normal (PLN) and PB (Poisson gamma) models were evaluated using two groups of California unsignalized intersections. Hypothetical treatment sites were selected from these datasets such that a significant effect would be estimated by the naive before-after method that does not account for regression to the mean. This study confirmed that FB methods can indeed provide valid results, in that they correctly estimate a treatment effect of zero at these hypothetical treatment sites after accounting for regression to the mean. Finally the EB and the validated FB before after methods were applied to evaluation of two treatments: the conversion of rural intersections from unsignalized to signalized control; and the conversion of road segments from a four-lane to a three-lane cross-section with two-way left turn lanes (also known as road diets). The result indicates that both FB and EB method can provide comparable treatment effect estimates. This would suggest it is still appropriate to conduct treatment effect analysis using the EB method for univariate crash data, but that it is essential in so doing to account for temporal trends in crash frequency.
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 | 0.079 | 0.199 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.003 | 0.006 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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".