Bibliographic record
Abstract
The statistical analysis of vehicle crash accident data is generally problematic. Data from commonly used sources is almost never without error and complete. Consequently, many analyses are contaminated with modeling and system identification errors. In some cases the effect of influential factors such as crash severity (the most significant component being speed) driver behavior prior to the crash, etc. on vehicle and occupant outcome is not adequately addressed. The speed that the vehicle is traveling at the initiation of a crash is a significant contributor to occupant risk. Not incorporating it may make an accident analysis irrelevant; however, despite its importance this information is not included in many of the commonly used crash data bases, such as the Fatality Analysis Reporting System (FARS). Missing speed information can result in potential errors propagating throughout the analysis, unless a method is developed to account for the missing information. In this paper, a method is presented to estimate the effect of missing speed information on the statistical effect of different variables (age, vehicle mass, …) on injury or fatality. The method developed uses historical data, such as the crash velocity distributions and the injury as a function of velocity -obtained from the National Accident Sampling System/Crash Data System (NASS/ CDS)- to estimate the modeling errors or the confounding effect expected from not considering the velocity factor in accident analysis. The method can be used to correct the level of statistical significance or to adjust the potential effect of explanatory crash variables, obtained from an accident analysis, when there is missing velocity information. Examples are provided where the suggested analytical procedure is used to estimate the confidence intervals for previously published risk of fatality based on crash data as well as to estimate a factor effect adjustment due to the missing speed data.
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 | 0.014 | 0.079 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.003 | 0.004 |
| Scholarly communication | 0.014 | 0.019 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.006 | 0.008 |
| Insufficient payload (model declined to judge) | 0.095 | 0.049 |
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".