problems in forecast -command with two variables
Posted: Thu Mar 27, 2008 2:01 pmDear All,
The attached file example1a.mod shows how forecast command operates, when there is one varexo_det variable. Note, however, that there have to be "periods 0:1;" in the shocks spesification. Without "0:" part, the code results error message.
When I add the second varexo_det variable (see attached file example1b.mod), I obtain the following error
It seems that the problem lies on the last two matrices in simultxdet at 57. One of them is 1 by 2 and other one 2 by 1.
I have tried this on a latest dynare 3 snapshot too.
Is there any simple workaround?
Best regards,
Antti
The attached file example1a.mod shows how forecast command operates, when there is one varexo_det variable. Note, however, that there have to be "periods 0:1;" in the shocks spesification. Without "0:" part, the code results error message.
When I add the second varexo_det variable (see attached file example1b.mod), I obtain the following error
- Code: Select all
??? Error using ==> minus
Matrix dimensions must agree.
Error in ==> simultxdet at 57
y_(dr.order_var,i) = y_(dr.order_var,i) + dr.ghud{j}*(ex_det(i+j-1,:)'-exe_det_');
Error in ==> forecast at 30
[yf,int_width] = simultxdet(y0,dr_,ex,ex_det_,options_.order, ...
Error in ==> example1b at 126
forecast(var_list_);
Error in ==> dynare at 26
evalin('base',fname) ;
It seems that the problem lies on the last two matrices in simultxdet at 57. One of them is 1 by 2 and other one 2 by 1.
I have tried this on a latest dynare 3 snapshot too.
Is there any simple workaround?
Best regards,
Antti