Hi,
I have built a macroeconomic model on EViews 12 and am trying to run some sensitivity analyses to understand the influence of the main exogenous parameters on the results of the model. I know that I can manually change the values of the parameters in different scenarios, but was wondering whether EViews is able to do this automatically.
More specifically, I would like to give an interval of values to an exogenous parameter A and let EViews draw from that interval and run different simulations, one for each value of parameter A.
Apologies if this is a naive question, but I have not found any thread related to this issue on the forum!
Sensitivity analysis help
Moderators: EViews Gareth, EViews Moderator
-
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13323
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Sensitivity analysis help
This is not built in, no. But writing a for loop in an EViews program is possible.
Follow us on Twitter @IHSEViews
Re: Sensitivity analysis help
Hi Gareth,
Thanks for your reply. I have partly addressed the problem, but I still have a question.
I tried something like this:
for !i = 1 to 15
model_name.scenario(a= !i) "scenario 1"
smpl 2010 @last
investment_sensitivity = y(!i)
smpl 2028 @last
model_name.solve(i=p, o=b)
next
Where y is a vector of random values.
In this way, EViews solves for 15 scenarios, but it then actually considers only scenario 1 as the only alternative scenario, i.e. each new scenario overrides the value of the past scenario. So although I have 16 aliased variables (from _0 to _15), there are only baseline scenario and scenario 1. How can I name each scenario as scenario 1, scenario 2 etc... within the for loop? If I try:
for !i = 1 to 15
model_name.scenario(a= !i) "scenario !i"
I receive the error message "Scenario not found". Any idea?
Many thanks for your help!
Thanks for your reply. I have partly addressed the problem, but I still have a question.
I tried something like this:
for !i = 1 to 15
model_name.scenario(a= !i) "scenario 1"
smpl 2010 @last
investment_sensitivity = y(!i)
smpl 2028 @last
model_name.solve(i=p, o=b)
next
Where y is a vector of random values.
In this way, EViews solves for 15 scenarios, but it then actually considers only scenario 1 as the only alternative scenario, i.e. each new scenario overrides the value of the past scenario. So although I have 16 aliased variables (from _0 to _15), there are only baseline scenario and scenario 1. How can I name each scenario as scenario 1, scenario 2 etc... within the for loop? If I try:
for !i = 1 to 15
model_name.scenario(a= !i) "scenario !i"
I receive the error message "Scenario not found". Any idea?
Many thanks for your help!
Who is online
Users browsing this forum: No registered users and 9 guests