Filtern
Dokumenttyp
- Konferenzveröffentlichung (3) (entfernen)
Schlagworte
- Accident (3)
- Statistics (3)
- Statistik (3)
- Unfall (3)
- Analyse (math) (2)
- Analysis (math) (2)
- Conference (2)
- Data acquisition (2)
- Datenerfassung (2)
- Fahrzeug (2)
Empirical vehicle crashworthiness studies are usually based on national or in-depth traffic accident surveys: Data on accident-involved cars/drivers are analysed in order to quantify the chance of driver injury and to assess certain risk factors like car make and model. As the cars/drivers involved in the same accident form a "cluster", where the size of the cluster equals the number of accident-involved parties, traffic accident survey data are typical multi-level data with accidents as first-level or primary and cars/drivers as secondlevel or secondary units (car occupants in general are to be considered as third level units). Consequently, appropriate statistical multi-level models are to be used for driver injury risk estimation purposes as these models properly account for the cluster structure of traffic accident survey data. In recent years various types of regression models for clustered data have been developed in the statistical sciences. This paper presents multi-level statistical models, which are generally applicable for vehicle crashworthiness assessment in the sense that data on single and multiple car crashes can be analysed simultaneously. As a special case of multi-level modelling driver injury risk estimation based on paired-by-collision car/driver data is considered. It is demonstrated that assessment results may be seriously biased, if the cluster structure inherent in traffic accident survey data is erroneously ignored in the data analysis stage.
Data concerning accidents involving personal injury which have been collected in the context of in-depth investigations on scene in the Hannover area since 1973 and in the Dresden area since 1999 represent an important basis for empirical traffic safety research. At national and international level various analyses and comparisons are carried out on the basis of "in-depth data" from the above mentioned investigations. In-depth data play a decisive role e.g. within the validation of EuroNCAP results on secondary safety (crashworthiness) of individual passenger car models. Thus, statistically sound methods of data analysis and population parameter estimation are of high importance. Since the 1st of August 1984 the "in-depth investigations on scene" in the Hannover area have been carried out according to a sampling plan developed by HAUTZINGER in the context of a research project on behalf of BASt. In the meantime a second region of in-depth investigation on scene was added with surveys in Dresden and the surrounding area. Internationally, the acronym GIDAS (German In-Depth Accident Study) is commonly used for the two above mentioned surveys. The objective of a current research project (topic of this contribution) is, among other things, to examine and adjust the previous weighting and expansion method for the two regional accident investigations to the current general conditions.
Crash involvement studies using routine accident and exposure data : a case for case-control designs
(2009)
Fortunately, accident involvement is a rare event: the chance of an individual road user trip to end up in a crash is close to zero. Thus, according to general epidemiological principles one can expect the case-control study design to be especially suitable for quantifying the relative risk (odds ratio) of accident involvement of road users with a certain risk factor as compared to road users that do not have this characteristic. Ideally, of course, the database for such a case-control study should be established by drawing two independent random samples of cases (accidental units) and controls (nonaccidental units), respectively. If, however, special data collection is not an option, it is nevertheless possible to analyze routine accident and exposure data under a case-control design in order to fully exploit the information contained in already existing databases. As a prerequisite, accident and exposure data from different sources are to be combined in a single file of micro or grouped data in a way consistent with the case-control study design. Among other things, the proposed methodological approach offers the possibility to use in-depth data of the GIDAS type also in investigations of active vehicle safety by combining this data with appropriate vehicle trip data collected in mobility surveys.