Statistical modelling of extreme values: Application to calculate extreme flow at river Rasina

Abstract

Engineers are aware of the uncertainties associated with the probability distributions of natural phenomena or those involving human beings. Even if one knows the parent distribution, in a hypothetical case, its functional representation remains a problem. One can select an appropriate probability model in a practical situation, considering the data available, to describe the phenomenon of interest, and then estimate the parameters and assess the risks involved. The data of 27 annual maximum streamflows at river Rasina in south central Serbia from 1966 to 2008 were analyzed and modeled. Three extreme value models for the data were considered and compared. Subsequently, the required design value with a given return period of exceedance was obtained.

Keywords

• anderson-darling test
• design value
• frechet distribution
• general extreme value distribution
• goodness-of-fit
• gumbel distribution
• kolmogorov-smirnov test
• return period