National automotive sampling system (NASS) general estimates system (GES) : analytical user's manual, 1988-2000
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 (NASS) General Estimates System (GES), covering data from 1988 to 2000. Published by the National Highway Traffic Safety Administration (NHTSA), the manual addresses the need for reliable, nationally representative data to support highway safety programs, regulatory initiatives, and cost-benefit analyses. The GES focuses on police-reported crashes involving fatalities, injuries, or major property damage, excluding minor unreported incidents to concentrate on crashes of greatest public concern. The GES employs a complex, three-stage probability sampling design to ensure national representability. First, Primary Sampling Units (PSUs)—defined as central cities, surrounding counties, or groups of contiguous counties—are selected from 1,195 units across the United States, categorized by geographic region and urbanization type. Second, police jurisdictions within these PSUs are sampled with probability proportional to the number of crashes investigated. Third, Police Accident Reports (PARs) are selected from these jurisdictions, stratified into four groups based on vehicle type, injury severity, and towing status. Data collectors visit approximately 400 police agencies across 60 sites to obtain copies of selected PARs, which are then coded into electronic files by trained personnel. Personal identifiers are removed to protect privacy. In 2000, approximately 57,000 PARs were sampled and coded. The resulting data are organized into four SAS data sets: Accident, Vehicle/Driver, Person, and Event files. The Accident file details environmental and roadway conditions; the Vehicle/Driver file records vehicle characteristics and driver behaviors; the Person file captures information on all involved individuals, including injury severity; and the Event file, introduced in 2000, describes the sequence and nature of harmful events. To address missing data, the system utilizes univariate and hot-deck imputation techniques, creating imputed variables (marked with "_I" or "_H") alongside original data. National estimates are derived by applying specific weights to each record, accounting for the multi-stage sampling probabilities. These weights are periodically adjusted, such as in 1993–1995 and 1996–1998, to reflect shifts in crash distributions across geographic areas. The significance of the GES lies in its ability to provide statistically valid national estimates of crash characteristics, enabling researchers and policymakers to identify safety problems and evaluate interventions. The manual provides comprehensive documentation of variable definitions, coding changes over the years, and procedures for calculating estimates and their associated standard errors. By offering a standardized, probability-based dataset, the GES supports evidence-based decision-making in highway safety, allowing for the analysis of trends in crash causation, injury severity, and vehicle performance across diverse geographic and demographic contexts.
Key finding
The GES manual provides the standardized variable definitions, sampling weights, and imputation procedures necessary for researchers to generate national estimates from the 1988-2000 police-reported crash data.
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 (6 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 | 3 | 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