COMPARATIVE-EVALUATION OF FREQUENCY-DISTRIBUTIONS FOR LOUISIANA EXTREME RAINFALL

A comparative study of five popular frequency distributions and three parameter estimation methods was conducted by using 92 Louisiana rainf all data sets. Computed results showed that the log-Pearson type 3 (LP EAR3) distribution was the most appropriate probability distribution f or the Louisiana rainfall data. Furthermore, the method of moments was found to be the best estimation method for the LPEAR3 distribution ba sed on descriptive performance indices. A first-order error analysis w as performed on the parameters of the LPEAR3 distribution. Computed re sults showed that the predicted quantiles of the LPEAR3 distribution w ere most sensitive to the population mean and relatively insensitive t o the coefficient of the skewness of the distribution.