Quantification of the effectiveness of a safety function in passenger vehicles on the basis of real-world accident data

  • In this paper we deal with dierent statistical modeling of real world accident data in order to quantify the eectiveness of a safety function or a safety conguration (meaning a specic combination of safety functions) in vehicles. It is shown that the eectiveness can be estimated along the so-called relative risk, even if the eectiveness does depend on a confounding variable which may be categorical or continuous. For doing so a concrete statistical modeling is not necessary, that is the resulting estimate is of nonparametric nature. In a second step the quite usual and from a statistical point of view classical logistic regression modeling is investigated. Main emphasis has been laid on the understanding of the model and the interpretation of the occurring parameters. It is shown that the eectiveness of the safety function also can be detected via such a logistic approach and that relevant confounding variables can and should be taken into account. The interpretation of the parameters related to the confounder and the quantication of the in uence of the confounder is shown to be rather problematic. All the theoretical results are illuminated by numerical data examples.

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:J.-P. Kreiss, T. Zangmeister
URN (permanent link):urn:nbn:de:hbz:386-kluedo-16944
Serie (Series number):Berichte des Fraunhofer-Instituts für Techno- und Wirtschaftsmathematik (ITWM Report) (203)
Document Type:Report
Language of publication:English
Year of Completion:2011
Year of Publication:2011
Publishing Institute:Fraunhofer-Institut für Techno- und Wirtschaftsmathematik
GND-Keyword:logistic regression ; real-world accident data ; safety function ; statistical modeling
Faculties / Organisational entities:Fraunhofer (ITWM)
DDC-Cassification:510 Mathematik

$Rev: 12793 $