The standard models for statistical signal extraction assume that the signal and noise are
generated by linear Gaussian processes. The optimum filter weights for those models are
derived using the method of minimum mean square error. In the present work we study
the properties of signal extraction models under the assumption that signal/noise are
generated by symmetric stable processes. The optimum filter is obtained by the method of
minimum dispersion. The performance of the new filter is compared with their Gaussian
counterparts by simulation.