A New Algorithm to Testing Departure from Gaussianity of Stationary Process Based on Trispectrum

This paper provides a novel approach to the classical problem in wireless communication of testing the departure from Gaussianity of an independent and identically distributed stationary process. Theoretical analysis of the independent Gaussian process Trispectrum is given. Based on the analysis, a new test algorithm that exploits the low fluctuation of the Trispectrum is proposed. Simulation results show that the proposed algorithm has a better performance than those conventional tests, even for a relative small data size.