Maximum likelihood estimation of the logarithmic series distribution

From MaRDI portal





The existence and a fixed point approach for the MLE of the parameter of the logarithmic series distribution are discussed both for univariate and for multivariate cases. The method is compared with Newton's methods, the secant method (for the univariate case) and the projected gradient method (for the multivariate case). Finally, the convergence rate of the fixed point method is derived and numerical examples are given.











This page was built for publication: Maximum likelihood estimation of the logarithmic series distribution

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3323008)