Parameter Estimation for the Class a Middleton Model

摘要

The principal aim of this study is to propose an estimator of the parameters of the Class A impulsive noise model with desirable asymptotic properties, namely, consistency and asymptotic efficiency. Four estimators are proposed and analyzed. The inherent drawbacks of using some classical estimators to estimate the Class A parameters are identified and explained. In particular, a consistent, asymptotically normal, and asymptotically unbiased estimator of the model parameters which can be implemented easily is established via the method of moments. Though an analysis of the relative mean-norm error reveals this estimator's inefficiency, its use as a first approximation leads to a consistent and asymptotically efficient estimator (Moment/Newton-step procedure) of the parameters of the Class A model.