Multivariate time series analysis of SafetyNet data. SafetyNet, Building the European Road Safety Observatory, Workpackage 7, Deliverable 7.7.

Author(s)
Commandeur, J.J.F. Bijleveld, F.D. & Bergel, R.
Year
Abstract

This deliverable provides an application of theories and methods documented in Deliverables 7.4 and 7.5 of work package 7 of the SafetyNet project. In this deliverable, use of select analysis techniques is demonstrated through real world road safety analysis problems, using aggregate data which may not be available yet in SafetyNet databases. The prime goal of the analysis in this deliverable however is to demonstrate the analysis techniques, their features and their suitability to answer road safety questions. Consequent on this, the data used in the analysis was selected primarily for their demonstrative usefulness. This deliverable demonstrates the use of time series analysis techniques. In particular, structural time series models are developed and demonstrated for France and the Netherlands, as well as disaggregated models for two types of networks in France, and disaggregated models for several accident types in the Netherlands. It is demonstrated how road safety developments of the traffic volume, the number of accidents and the number of fatalities can be linked to the developments of exposure, accident risk and accident severity, estimated through their unobserved components: their trend (level and slope) and their seasonals. Some interpretations are given. In addition, the performance of the time series model is compared to the performance of one classical alternative: the vectorial regression model. (Author/publisher)

Request publication

5 + 0 =
Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.

Publication

Library number
20090804 ST [electronic version only]
Source

[S.l.], European Road Safety Observatory (ERSO) / Brussels, European Commission, Directorate-General Energy and Transport, 2007, 40 p., 12 ref.; Contract Number TREN-04-FP6TR-S12.395465/506723

SWOV publication

This is a publication by SWOV, or that SWOV has contributed to.