A Gibbs Sampling-based approach for parameter estimation of the EGK distribution

Abstract

We present a novel approach for estimating the parameters of the extended generalized-K (EGK) distribution commonly used as a fading model in wireless and optical communications links. The proposed method is based on the Gibbs sampling technique and does not require solving nonlinear equations nor performing numerical integrations. Numerical and simulation results are presented showing that the estimated and original distributions are virtually indistinguishable and formal metrics like Kullback-Leibler (KL) divergence, the mean integrated squared bias (MISB), the mean integrated variance (MIV) and the mean integrated squared error (MISE) all show excellent agreement between the two as well.