Using Naturalistic Driving Data to Examine Teen Driver Behaviors Present in Motor Vehicle Crashes, 2007-2015
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 study addresses the critical issue of distracted driving among teenage motorists, aiming to identify specific behavioral factors and temporal trends associated with motor vehicle crashes involving drivers aged 16–19. The research was motivated by significant discrepancies between official government statistics and observational data; while police reports indicated that only 10% of teen drivers in fatal crashes were distracted in 2014, previous AAA Foundation research suggested distraction played a role in nearly 60% of moderate-to-severe teen crashes. Experts believe official estimates substantially underestimate the prevalence of distraction, necessitating a more accurate assessment using naturalistic driving data. The methodology relied on analyzing in-vehicle video footage captured by Lytx DriveCam systems. The study expanded upon a prior dataset by adding 538 crashes recorded between August 2013 and April 2015 to the original 1,691 crashes from August 2007 to July 2013, resulting in a total sample of 2,229 eligible crashes. Participants were primarily located in the Midwest United States. Researchers examined the six seconds preceding each crash, focusing on major crash types including single-vehicle loss of control, single-vehicle road departure, rear-end, and angle collisions. Key findings reveal that an average of 59% of crashes involved some form of potentially distracting behavior in the six seconds prior to impact. The most frequent distractions were interacting with passengers and cell phone use. Passengers were present in 34% of crashes, with 84.8% of those passengers also being aged 16–19; drivers conversed or interacted with passengers in 15% of incidents. Cell phone use was observed in 12% of crashes, with a significant shift toward manual operation or visual attention (9%) rather than talking or listening (3%). This manual use was particularly prevalent in road-departure crashes (28%) and rear-end crashes (19%). Notably, in rear-end crashes, the average time eyes were off the road increased from 2.0 to 3.1 seconds over the study period, and the percentage of crashes where the driver showed no prior reaction rose from 13% in 2008 to 25% in 2014. The study concludes that distraction, particularly due to cell phone use, is far more prevalent than official National Highway Traffic Safety Administration statistics suggest, which attribute only 1% of all crashes to cell phone distraction. These findings imply that current official data significantly underreport the risk. Consequently, the authors recommend that driver education and training programs explicitly teach young drivers to avoid taking excessively long glances away from the forward roadway. The AAA Foundation also highlights resources such as Driver-ZED and StartSmart to help parents and teens manage these risks effectively.
Key finding
Between 2007 and 2015, an average of 59% of teen driver crashes captured on in-vehicle video contained potentially distracting behavior in the six seconds before impact, with cell phone use present in 12% of crashes—substantially exceeding official distraction rates derived from police reports.
Methodology
naturalistic
Sample size: N=2,229 eligible teen driver crashes (ages 16–19; Lytx DriveCam video, August 2007–April 2015)
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_aaa_foundation on 2026-05-23 (5 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | aaa_foundation | — | — | 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 | 2 | 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: observational prevalence, crash risk outcomes
- Methodological Resource: dataset resource