Abstract: The influence of some road geometrical parameters and characteristics of road vicinity on traffic safety has been identified and measured in the work. The real data of multi-vehicle accidents without pedestrians on non-urban roads for a chosen region of Poland is the object of the research. Logistic regression in the form of proportional odds ratio model and continuation ratio logits models have been investigsted in the analysis. The treat on the road is represented by the accident severity, which is an ordered response variable subiect to the classification task. The modeling results indicate that the following features have statistically significant influence on the accident severity: type of shoulders on both sides of a roadway, area type, pedestrian sidewalks, presence or absence of intersection.
B I B L I O G R A F I A1. Agresti A., An Introduction to Categorical Data Analysis. A Wiley Interscience Publication JOHN WILWEY & SONS INC, 1996.
2. Al-Ghamdi A., Using logistc regression to estimate the influence of accident factors on accident severity. Accident Analysis & Prevention, Elsevier 2002, No. 34, s 729-741.
3. Cichosz P.: Systemy uczące się. Warszawa, WN-T 2000.
4. Deng Z., Ivan J., Garder P., Analysis of Factors Affecting the Severity of Head-On Crashes. Two-Lane Rural Highways in Connecticut. In Transportation Research Record: Journal of the Transportation Research Board, No 1953, TRB, National Research Board of the National Academies, Washington, D.C. 2006 s. 137-146.
5. Donnel E.T., Mason J.M. Jr., Predicting the Severity of Median-Related Crashes in Pennsylvania by Using Logistic Regression. In Transportation Research Record: Jounnal of the Transportation Research Board, No 1897, TRB, National Research Council Washington, D.C. 2004, s. 55-63.
6. Giudici P., Applied Data Mining. New York: Wiley & Sons 2002.
7. Hand D., Mannila H., Smyth P., Eksploracja danych. Warszawa, WN-T 2005.
8. Jobson J. D., Applied Multivariate Data Analysis. Springer-Verlag 1992.
9. Kopelias P., Papadimitriou F., Papandreou K., Prevedouros P., Urban Freeway Crash analysis - Geometric, Operational and Weather Effects on Crash Number and Severity. 2007 Annual Meeting of the Transportation Research Board, Washington, D.C. 2007.
10. Lenguerrand E., Martin J., Laumon B., Modelling the hierarchical structure of crash data. Application to severity analysis. Accident Analysis and Prevention. Elsevier 2006, No. 38, s. 43-53.
11. Nowakowska M., Dane o elementach drogi i jej otoczenia w miejscu zajścia zdarzenia drogowego. Nepublikowane materiały do własnych prac badawczych realizowanych w Politechnice Świętokrzyskej nt. modelowania zagrożeń na drogach zamiejskich, Kielce 2008-2000.
12. Read T., Cressie N., Goodness-of-Fit Statistics for Discrete Multivariate Data, Springer-Verlag 1988.
13. Tabachnick B.G. and L.S.. Fidell, Using Multivariate Statistics. HarperCollinsCollegePublishers, New York, 1996.
14. Wytyczne projektowania dróg II, IV i V klasy technicznej. Opracowanie pod kierunkem T Sandeckiego, Generalna Dyrekcja Dróg Krajowych i Autostrad, Warszawa 1995.
15. Zarządzenie Nr 635 Komendanta Głównego Policji z dnia 30 czerwca 2006 r. w sprawie metod i form prowadzenia przez Policję statystyki zdarzeń drogowych. Warszawa 2006. 
YADDA/CEON