Description and Causal Inference of Short-term Small-number Collisionsby Data Visualizations
Bibliographic record
Abstract
Collisions are rare random events. Particular collision dataitems within specific temporal or spatial units,e. g.,daily fatal and injury collisions of a small or medium sized city,are generally small numbers( say,0- 25). These small-numbered collisions are inadaptable to be analyzed and predicted by conventional approaches. For methods with continuous variables, such as generalized linear model( GLM),this type of data has limited value range,too high randomness and variation,so that statistically significant( SS) results are unlikely to be obtained. On another hand,for methods with discrete variables,e. g.,the Logit Model,this type of data has too many classifications and therefore it is hard to be properly fitted. This paperworks on a solution to unravel this dilemma through newly developed data visualization approaches. Based on the sample data from a Canadian city,a series of data visualization methods,including data decomposition,colored scatter-plot matrix,3D plots,were employed to describe collision patterns,and to identify its impact factors and figure out the interactions among the factors.Then,the graphic model,as a particular causal inference method,was introduced in order to establish intrinsic connections from collisions to causal factors and to draw causal structure among factors.Moreover,the causal effects between each particular factor and the collision were quantitatively estimated. This study, combined with descriptive and inferential methods, fills the methodological vacancy for the short-time small-numbered collision data and outcomes of this study can be directly utilized to support real-time safety management and control,pre-scheduling and effect evaluation for safety countermeasures across multiple disciplines such as traffic management,enforcement,and road maintenance.
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 | 0.013 | 0.052 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.008 | 0.009 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 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".