Estimation of ARMA parameters using third order cumulants

Within the last few years, the field of higher order statistics (HOS) has emerged rapidly for analyzing non-Gaussian processes. In the past, HOS methods were mostly theoretical. However, with the rapid increase in computing capability, these theoretical methods have begun to be applied in practice. There are several reasons behind the use of HOS. The work presented here is mainly based on the property that cumulants are blind to any kind of Gaussian process. Hence, when the processed signal is non-Gaussian and the additive noise is Gaussian, the noise will vanish in the cumulant domain. We have addressed the problem of estimating the parameters of a non-Gaussian autoregressive moving-average (ARMA) process