A NON-GAUSSIAN MODEL FOR INDIAN MONSOON RAINFALL

A non-Gaussian model as a function of Gaussian process is developed in this paper for Indian monsoon rainfall time series. The functions of a Gaussian process are the Hermite polynomials. The unknown coefficients of the Hermite polynomials are found with the help of the first four moments of the given data. Since the probability density function of the Gaussian process is known, the non-Gaussian density function for the rainfall process is found by using the transformation on the known Gaussian density function numerically. Sample histogram of the data and the non-Gaussian density function are compared graphically along with the Gaussian density function. This clearly justifies that the non-Gaussian density better compares with the data distribution. This exercise has been done on the four broad regions of India identified by Indian Meteorological Department (IMD) and also for one subdivision of Karnataka. It has been observed that at 5% significance level, this model is able to reproduce the probability structure of the rainfall time series at different spatial scales studied.