Novel Low-Complexity Estimators for the Shape Parameter of the Generalized Gaussian Distribution

Four new moment-based estimators are proposed for the shape parameter of the generalized Gaussian distribution. The new moment-based estimators have simple structures. They also outperform previous known moment-based estimators when the true value of the shape parameter is small. Simulation results show that in some cases, the estimation error in the proposed moment-based estimators is less than half of the error observed in current moment-based estimators.