Page 1 of 1
Coeficient vector C: sepcification
Posted: Tue Oct 08, 2013 12:55 am
by frhes
Is there any information available how the dimension of the coefficient vector is specified by Eviews internally and how it could be modified? I am confronted with a 750 x 1 coefficient vector in a state space model which prevents yhe estimation of the Kalman filter due to insufficient observations. The dimension of this coefficient vector does not respond to the specifications of my state-space model.
Re: Coeficient vector C: sepcification
Posted: Tue Oct 08, 2013 7:47 am
by EViews Gareth
It is a 750 row vector. What more do you need to know?
Re: Coeficient vector C: sepcification
Posted: Tue Oct 08, 2013 8:20 am
by frhes
Indeed it is a 750 row vector, but how did EVIEWS choose the number of rows? And why does this number not react to respecifications of the state space model which change the number of coefficients?
Re: Coeficient vector C: sepcification
Posted: Tue Oct 08, 2013 8:30 am
by EViews Gareth
It is always 750. EViews doesn't choose the size. It is always 750.
Re: Coeficient vector C: sepcification
Posted: Tue Oct 08, 2013 9:36 am
by startz
EViews sets aside 750 spaces in C, but doesn't use the ones that don't show up in the model.