Abstract

The Nakagami distribution is a popular distribution widely used in wireless communications. In order to model certain aspects of failure data, the inverse Nakagami distribution is often used. The inverse Nakagami distribution does not have closed-form maximum likelihood estimators. Closed-form estimators by adapting the method of moments are proposed. Also proposed is a bias corrected version of the estimators. Large sample properties including asymptotic variances of the proposed estimators are derived. A simulation study and data applications are provided to compare the performances of the maximum likelihood estimators, the proposed estimators and their bias corrected versions. The simulation study showed that the proposed and maximum likelihood estimators perform equally well.