Abstract
In accident reconstruction, individual road accidents are treated as essentially deterministic events, although incomplete information can leave one uncertain about how exactly an accident happened. In statistical studies, on the other hand, accidents are treated as individually random, although the parameters governing their probability distributions may be modeled deterministically. Here, a simple deterministic model of a vehicle/pedestrian encounter is used to illustrate how naïvely applying statistical methods to aggregated data could lead to an ecological fallacy and to Simpson's paradox. It is suggested that these problems occur because the statistical regularities observed in accident data have no independent status, but are simply the result of aggregating particular types and frequencies of mechanisms.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1119-1127 |
| Number of pages | 9 |
| Journal | Accident Analysis and Prevention |
| Volume | 36 |
| Issue number | 6 |
| DOIs | |
| State | Published - Nov 2004 |
Bibliographical note
Funding Information:The author would like to thank Kate Sanderson and Sujay Davuluri for data collection and analysis support. Ezra Hauer and an anonymous referee commented on an earlier version of this paper, leading to substantial improvements. This research was supported in part by Minnesota’s Local Road Research Board and in part by the Intelligent Transportation Systems Institute at the University of Minnesota. However, all facts, conclusions, and opinions expressed here are solely the responsibility of the author.
Keywords
- Causal mechanisms
- Crash prediction models
- Ecological fallacy
- Simpson's paradox
