<< kalman Kalman filter estimation tvp >>

Grocer >> Kalman filter estimation > smoothing

smoothing

Kalman smoother

CALLING SEQUENCE

[betas,sigmas]=smoothing(F,betat,betaf,sigmat,sigmaf, begsmooth)

PARAMETERS

Input

* F = transition matrix

* betat = vector of filtered beta at date t with the information available at date t (beta(t|t))

* betaf = vector of filtered beta at date t with the information available at date t-1 (beta(t|t-1)

* sigmat = vector of filtered variances at date t with the information available at date t (sigma(t|t))

* sigmat = vector of filtered variances at date t with the information available at date t-1 (sigma(t|t-1))

* begsmooth = first observation where to calculate smoothed values

 

Output

* betas = vector of smoothed beta at date t with the information available at date T (beta(t|T)

* sigmat = vector of smoothed variances at date t with the information available at date T (sigma(t|T))

DESCRIPTION

Provides smoothed values from a Kalman filtering.

EXAMPLE

// smoothing is a used by the function kalman:
[betas,sigmats]=smooth(grocer_F,betat,betaf,sigmatt,sigmatf)

AUTHOR

Eric Dubois 2002

Report an issue
<< kalman Kalman filter estimation tvp >>