<< filter Kalman filter estimation kalman >>

Grocer >> Kalman filter estimation > filter_like

filter_like

Kalman filter log-likelihood

CALLING SEQUENCE

[llik]=filter_like(param,func,y,x,F,z)

PARAMETERS

Input

* param = a vector of parameters (sqrt of variances)

* func = the function which transforms the parameters into the matrix of variances (Q and R)

* y = (nx1) data vector

* x = (nxk) data matrix

* F = transition matrix

* z = (nxl) data matrix

 

Output

* llik = - 2*log-likehood (+n*log(2*%pi))

DESCRIPTION

Generates model loglikelihood in a kalman model: y(t) = X(t)*B(t) + Z(t)*A + e(t), e(t) = N(0,R) B(t) = F*B(t-1) + v(t), v(t) = N(0,Q)

EXAMPLE

// Filter_like is used by the function kalman:
oresult = maxlik(filter_like,grocer_param,grocer_func,grocer_y,grocer_x,grocer_F, varargin(:))

AUTHOR

Eric Dubois 2002

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