A new method for evaluating the log-likelihood gradient (score) of linear dynamic systems

DOI10.1109/9.1295zbMath0649.93079OpenAlexW2151310296MaRDI QIDQ3795597

Mordechai Segal, Ehud Weinstein

Publication date: 1988

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/9.1295

zbMATH Keywords

maximum likelihood estimationlinear dynamic systemsgradient-search algorithmslog-likelihood gradientoptimal smoothing equations

Mathematics Subject Classification ID

Related Items (6)

Discussion on: ``Generalized linear dynamic factor models: an approach via singular autoregressions ⋮ An algorithm for the exact Fisher information matrix of vector ARMAX time series ⋮ SVD-based state and parameter estimation approach for generalized Kalman filtering with application to GARCH-in-Mean estimation ⋮ A unified square-root approach for the score and Fisher information matrix computation in linear dynamic systems ⋮ Constructing numerically stable Kalman filter-based algorithms for gradient-based adaptive filtering ⋮ Maximum likelihood estimation via the extended covariance and combined square-root filters

This page was built for publication: A new method for evaluating the log-likelihood gradient (score) of linear dynamic systems