National automotive sampling system (NASS) general estimates system (GES) : analytical user's manual, 1988-1999
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This document serves as the analytical user’s manual for the National Automotive Sampling System General Estimates System (GES), a dataset maintained by the National Highway Traffic Safety Administration (NHTSA) covering the years 1988 through 1999. The GES was established to provide nationally representative data on police-reported motor vehicle crashes, supporting the development and assessment of highway safety programs. By focusing on crashes resulting in fatalities, injuries, or significant property damage, the system aims to identify safety problems and facilitate cost-benefit analyses for regulatory initiatives. The GES data are derived from a probability sample of approximately 6.4 million annual police-reported crashes. The sampling design involves three stages: selecting Primary Sampling Units (PSUs) across 1,195 geographic areas; sampling police jurisdictions within those PSUs proportional to crash volume; and selecting specific Police Accident Reports (PARs) stratified by crash severity and vehicle type. Data collectors visit roughly 400 police agencies across 60 sites to obtain PARs, which are then coded into electronic files by contractors. To protect privacy, personal identifiers are excluded. The resulting data are organized into three SAS files: the Accident File (environmental and roadway conditions), the Vehicle/Driver File (vehicle characteristics and driver actions), and the Person File (demographics and injury severity). To address missing data, the GES employs two imputation methods: univariate imputation, which assigns values based on known proportions for a single variable, and hot-deck imputation, which uses correlated variables to find similar records for value assignment. National estimates are calculated using a weighting variable that accounts for the inverse probability of selection at each sampling stage. These weights are periodically adjusted to reflect shifts in crash distributions, with revisions implemented in 1993–1995 and 1996–1998. The manual provides detailed definitions for all variables, including codes for injury severity, collision types, and vehicle defects, enabling researchers to analyze crash characteristics and compute national estimates with associated standard errors.
Key finding
The GES provides a structured, probability-based dataset with specific weighting and imputation protocols to generate national estimates of police-reported traffic crashes from 1988 to 1999.
Methodology
dataset
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (45 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 42 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: crash risk outcomes
- Methodological Resource: dataset resource