I get the following message when I run the attached code.
Error using lnsrch1 (line 71)
Some element of Newton direction isn’t finite. Jacobian maybe singular or there is a problem with
initial values
I get the following message when I run the attached code.
Error using lnsrch1 (line 71)
Some element of Newton direction isn’t finite. Jacobian maybe singular or there is a problem with
initial values
There is no attachement.
prog05.mod (2.6 KB)
sorry. here’s the mod file.
Check your model. For example,
z = rhoz*z(-1)+ ez;
implies z= 0
. That conflicts with
m = ((z*(1-(chi*(1-sigma))))/((1-tau)*w*((kappa*exp(n))^(1-sigma))))^(1/(1-sigma));
where it should not be 0. I guess it should be exp(z)
in that equation.