A novel parametric estimation algorithm for non-Gaussian processes experiencing impulsive noise

Identifying the parameters of non-Gaussian processes perturbed by stochastic noise with impulses is a challenging task for researchers. The method of higher- order statistics is not well suited for analyzing non-Gaussian impulsive noise signals, which produce outliers. The authors propose the use of systems with impulse effect along with the well-known autoregressive moving average model to produce a parametric estimation algorithm to effectively model these particular processes without assuming ergodicity. A performance analysis is provided to showcase the novel algorithm.