OSR Optimal Simple Rules

[ManuelG]

Dear Community,

I am trying to use the OSR command to work out the optimal policy parameters in the Taylor rule.

However I just realised that the results change by changing the initial values of the parameters.
In the model attached for example the starting values are the usual (phipi = 1,5/ phiy = 0.5) and the algorithm picks as optimal values phipi = 26.25/ phiy = 1.62. In any way I change the initial conditions the results change.

Am I missing something?

Thanks
Manuel

OSR_welfare.mod (4.0 KB)

[jpfeifer]

Policy frontier

OSR means you are looking for a global optimum in your objective function. That global optimum should not depend on where you start looking for your optimum. If you get different optima depending on the starting values, some of them must be local ones. If that is what is causing your different results, you need to change your approach, e.g. by trying a global optimizer.

[ManuelG]

Dear Dr. Pfeifer,

thanks a lot for your help.

I thought that the algorithm picked by the command opt_algo=9 was a global optimizer. Is that not? and if not, which optimizer would be advisable?

Best Regards
Manuel

[jpfeifer]

Yes, it’s a global optimizer, but it may still get stuck at a local minimum. For that reason, testing different starting values is exactly what one should do.

[ManuelG]

Alright, I see, thanks for your help. I will stick with the same algorithm and try different initial values then.

Best Wishes
Manuel