INITIALIZING THE KALMAN FILTER FOR NONSTATIONARY TIME SERIES MODELS

By William Bell. 1991

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Release Strategies and the Social Impacts of Language Models (2019, background): “Black or African-American people account for 27% of arrests in 2017 [19] but only 13% of the U.S. population [11].”
Universally utility-maximizing privacy mechanisms (2008, background): “If the user maps outputs of the geometric mechanism that are at least ( n + 1) / 2 to n and all other outputs to 0, it eﬀectively induces a new mechanism with the much smaller expected loss of α ( n +1) / 2 / (1 + α ).”
Extended Kalman Filtering for Remaining-Useful-Life Estimation of Bearings (2015, background): “One important point in the implementation of EKF is the choice of the initial parameters, as the speed of convergence depends on the initial estimate x̂0 and the uncertainty matrix P0 [52].”
A Review of Some Modern Approaches to the Problem of Trend Extraction (2012, background): “The following references discuss the finite-sample theory from an SSF viewpoint: Bell & Hilmer (1991); De Jong (1991); Koopman (1997) and Durbin & Koopman (2001).”