R packages - Aug 2009 - New package for multivariate Kalman filtering, smoothing, simulation and forecasting

Dear all,

I am pleased to announce the CRAN release of a new package called 'KFAS'
-
Kalman filter and smoother.

The package KFAS contains functions of multivariate Kalman filter,
smoother, simulation smoother and forecasting. It uses univariate approach
algorithm (aka sequential processing), which is faster than normal method,
and it also allows mean square prediction error matrix Ft to be singular.
Filtering, smoothing and simulation functions are all written in Fortran.
Functions allow time-variant system matrices and missing observations. In
case distributions of some or all elements of initial state vector are
unknown, functions use exact diffuse initialisation.

I hope that this package will be useful for people working with state
space models and time series in general. Any feedback is appreciated.

Yours,

Jouni Lehtonen
University of Jyv?skyl?
Finland

_______________________________________________
R-packages mailing list
R-packages at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-packages

Hi,
I tried to manage exponential family state-space model with the packages
KFAS.
The problem is that my data set includes some NA observation and it seems
not working.
Any suggestion?

Thanks in advance,

Federico

-- 
View this message in context:
http://r.789695.n4.nabble.com/R-pkgs-New-package-for-multivariate-Kalman-filtering-smoothing-simulation-and-forecasting-tp903589p3027907.html
Sent from the R help mailing list archive at Nabble.com.