Abstract
Abstract For a moderately large number of years of observations the quantiles of rainfall totals for individual months can be estimated from ranked values. With only a few years of observations it is necessary to estimate the quantiles from a distribution fitted to the data for all months. The Compound‐Poisson distribution can utilise the information available in rainfall totals for all months to give reasonably precise parameter estimates for individual months. Representative parameters can be obtained from as few as 10 years of data. Quantiles are calculated from, and statistically qualified by, the estimated mean and covariance structure of the fitted parameters.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
