The application of Jenkinson's method to extremal distributions for low probability annual extremes of rainfall and stream flow is studied and discussed.

A statistical method devised by Jenkinson has been examined and compared with other methods of fitting extreme value distributions to observed data. The Jenkinson method, being strictly objective, has the particular advantage of taking into account the extreme part of the extreme value distribution. The author shows, by applying the Jenkinson method to extreme values which significantly belong to several different kinds of frequency distributions, that this method could be applied as a standard one. Finally, the author indicates the possibility of using the Jenkinson method to extrapolate statistical characteristics from a series of statistically unstable short-term data.