This paper tackles the analysis of the Extensive CAncellation (ECA) filter effects in the statistical characterization of ground radar clutter. Real radar databases acquired by a DVB-T based Passive Radar (PR) system were characterized considering the Cross-Ambiguity Function output as the observation space. Goodness-of-fit tests were applied, and skewness and kurtosis values were estimated. The Gaussian model was proved to be suitable for high Doppler shifts. However, Mixture of Gammas and Gaussians distributions were proposed to model the intensity and the in-phase and quadrature components, respectively, of the region centred in the zero Doppler line. These results prove that, although the ECA filter rejects the most part of the interference components, a non-homogeneous characterization was required for Doppler shifts close to zero, where ground clutter effects concentrate. The proposed theoretical distributions will be useful for the formulation of optimum detectors based on the Neyman-Pearson criterion, improving the detection performance of PR systems.