Title :
Characterization of the LAD (L1) AR parameter estimator when applied to stationary ARMA, MA, and higher order AR processes
Author :
Olsen, Elwood T. ; Ruzinsky, Steven A.
Author_Institution :
Illinois Inst. of Technol., Chicago, IL, USA
fDate :
9/1/1989 12:00:00 AM
Abstract :
It is shown that least absolute deviation (LAD) autoregressive (AR) estimates converge to the parameters of an nth-order finite-impulse-response (FIR) filter which minimizes the expectation of the absolute value of the prediction error. Examples are presented in which these parameters are calculated and the efficiencies of the LAD estimates are determined from a Monte Carlo simulation. Applications to order selection and PARCOR parameter estimation are discussed
Keywords :
digital filters; filtering and prediction theory; ARMA; Monte Carlo simulation; PARCOR; autoregressive; digital filters; filter; finite-impulse-response; least absolute deviation; parameter estimator; Convergence; Equations; Finite impulse response filter; Least squares approximation; Mathematics; Parameter estimation; Probability density function; Random variables; Speech; Telecommunications;
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on
