Title :
Maximum-likelihood symmetric α-stable parameter estimation
fDate :
5/1/1999 12:00:00 AM
Abstract :
Using the close relation between Fisher scoring and Newton maximization, and an efficient density function evaluation, we develop a fast maximum-likelihood parameter estimation method. Simulations show the algorithm to be superior in accuracy to McCulloch´s (1986) method and to achieve the Cramer-Rao bound
Keywords :
Newton method; maximum likelihood estimation; numerical stability; optimisation; signal processing; statistical analysis; Cramer-Rao bound; Fisher scoring; McCulloch´s method; Newton maximization; efficient density function evaluation; fast MLE method; impulsive signals model; maximum-likelihood estimation; simulations; symmetric α-stable parameter estimation; Acoustic noise; Astronomy; Atmospheric modeling; Density functional theory; Low-frequency noise; Maximum likelihood estimation; Newton method; Parameter estimation; Signal processing; Underwater acoustics;
Journal_Title :
Signal Processing, IEEE Transactions on
