Tag: extended Kalman filter

R code for forecasting with the extended Kalman filter

In my previous blog post I demonstrated how to implement and use the extended Kalman filter (EKF) in R. In this post I will show how to predict future system states and observations with the EKF. extended Kalman filter forecasting Continue reading R code for forecasting with the extended Kalman filter

Posted on February 16, 2016June 14, 2016Tags extended Kalman filter, forecasting, nonlinear dynamic model, nonlinear Kalman filtering, state space model

R code for estimating the parameters of an extended Kalman filter model using likelihood maximization

In my previous blog post I showed how to implement and use the extended Kalman filter (EKF) in R. In this post I will demonstrate how to fit unknown parameters of an EKF model by means of likelihood maximization. extended Kalman filer MLE Continue reading R code for estimating the parameters of an extended Kalman filter model using likelihood maximization

Posted on February 15, 2016June 14, 2016Tags extended Kalman filter, maximum likelihood estimation, nonlinear dynamic model, nonlinear Kalman filtering, state space model

R code for implementing the extended Kalman filter

The code below implements the discrete-time extended Kalman filter (EKF) in R.

For numerical stability and precision the implemented EKF uses a Singular Value Decomposition (SVD) based square root filter. For a description of this SVD-based square root filter see Appendix B of Petris and colleagues’ 2009 book Dynamic linear models with R. Continue reading R code for implementing the extended Kalman filter

Posted on February 11, 2016June 15, 2016Tags extended Kalman filter, first-order EKF, nonlinear dynamic model, nonlinear Kalman filtering, state space model, Taylor series expansion