Structural VAR Estimation

[Mutawakil]

I am trying to a estimate a structural VAR in Eview. After constructing the A and B matrices with identifying restrictions, I then proceeded to estimate the structural VAR, but I obtained an error message saying"Hessian of structural VAR likelihood is singular at starting values. Reset starting values or specify restrictions to ensure that the model is (locally) identified".
I am stuck with this error message and I wanted to ask if anyone can assist me to overcome this problem.
Thank you

[EViews Gareth]

Did you try different starting values?

[Mutawakil]

How do I set the starting values in the first place?

[EViews Gareth]

Use the Optimization Control tab of the Structural VAR dialog.