GAM Modelling of Daily Number of Traffic Accidents as a Function of Meteorological Variables in the Czech Republic

Petra Kolísková and Jiří Neubauer
Additional contact information
Petra Kolísková: University of Defence, Brno, Czech Republic
Jiří Neubauer: University of Defence, Brno, Czech Republic

European Journal of Business Science and Technology, 2025, vol. 11, issue 1, 23-38

Abstract: Meteorological conditions exert a considerable influence on traffic patterns. This paper examines the influence of meteorological variables on the daily number of traffic accidents requiring fire brigade intervention. The influence of meteorological variables, including maximum temperature, wind speed, air pressure, precipitation, snow cover and sunshine, was examined. A Generalized Additive Model for variables with a Poisson distribution was employed for modelling purposes, as this allows for the representation of non-linear dependencies. The analysis demonstrates that the lowest incidence of accidents occurs at temperatures approximating 10 °C. The average daily number of accidents increases with windy weather, the minimum number of accidents occurs at zero precipitation, and the accident rate rises with higher levels of sunshine. In the Czech Republic, the period of greatest risk in terms of road traffic accidents is the summer and winter months. The findings may have several practical applications, for example, in the improvement of meteorological warnings in traffic.

Keywords: traffic accidents; integrated rescue system; weather; Poisson distribution; generalised additive model (search for similar items in EconPapers)
JEL-codes: C02 C51 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://ejobsat.cz/doi/10.11118/ejobsat.2024.014.html (text/html)
http://ejobsat.cz/doi/10.11118/ejobsat.2024.014.pdf (application/pdf)
free of charge

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:men:journl:v:11:y:2025:i:1:p:23-38

DOI: 10.11118/ejobsat.2024.014

Access Statistics for this article

European Journal of Business Science and Technology is currently edited by Svatopluk Kapounek

More articles in European Journal of Business Science and Technology from Mendel University in Brno, Faculty of Business and Economics Contact information at EDIRC.
Bibliographic data for series maintained by Ivo Andrle ().