6 Empirical Investigation 142
Chapter 6 Empirical Investigation The aim of our research here is to evaluate the quality of MC (algorithm 5.3.1) empirically. Therefore, we compare its perfor- mance to a CC system using data gained from the analysis of military road accidents which occurred in 2007. To this end, we construct a collective which mirrors the set of those members of the Bundeswehr who operated a company car in the considered time period. 6.1 Organization of the Data 6.1.1 Description of the Data Sets Our raw data consist of two parts: (1) Information concerning road accidents associated with stan- dard passenger cars operated by the Bundeswehr in Jan- uary, February, June and July 2007 and (mainly) caused by military staﬀ1. These data were provided by ZMK 1This restriction was made to picture the situation of a third party liability insurance. (Zentrale Militärkraftfahrtstelle), the approval authorities for military vehicles. In the data base of ZMK, informa- tion concerning road accidents are collected according to a special form, the notice of accident (Meldung über den Kraftfahrzeugunfall). (2) Further, the structure of the Bundeswehr according to mil- itary rank and age, more precisely, the absolute frequen- cies of all age-rank-tuples is available (valuation date: De- cember 2007). This was provided by BMVg (Bundesmin- isterium der Verteidigung). The data for July serve to evaluate the performance by means of a prognostive test to be described later of our model, so that we use solely the data from the three months January, February and June...
You are not authenticated to view the full text of this chapter or article.
This site requires a subscription or purchase to access the full text of books or journals.
Do you have any questions? Contact us.Or login to access all content.