Hi,
I use EViews 9. I have built a system of equations and run a stochastic simulation in the solve interface. EViews interface provides some outputs like Mean+/- 2 SD for each forecast. I have several questions:
1- I would be interested in getting other outputs such as median and other percentiles of the distributions for my forecasts, is there another way to get those in the interface without writing code ?
2- Is there a way to access the data related to the stochastic simulation in the interface ? (ie: all the iterations)
3- Is there a built in way to pull out some fan charts if I can get these data ?
Thanks for your answer.
Regards,
Reach data of a stochastic simulation for error bounds
Moderators: EViews Gareth, EViews Moderator
-
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13317
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Reach data of a stochastic simulation for error bounds
On the solve dialog there is a page called Stochastic Options. One of the fields there lets you create a page in which all the stochastic iterations will be saved.
Follow us on Twitter @IHSEViews
Re: Reach data of a stochastic simulation for error bounds
Thanks,
Any idea for the fan charts ?
Regards,
R
Any idea for the fan charts ?
Regards,
R
-
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13317
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Reach data of a stochastic simulation for error bounds
You'll have to be more precise
Follow us on Twitter @IHSEViews
Re: Reach data of a stochastic simulation for error bounds
Hi Gareth,
Thanks for your answer.
Just other users information, I found what I needed for my fan charts statistics using the @quantilesby function. The function allows to compute different quantiles by value of a cross section (useful with panel data). These values can then be used in a mixed graph using the "band" option.
Regards,
R
Thanks for your answer.
Just other users information, I found what I needed for my fan charts statistics using the @quantilesby function. The function allows to compute different quantiles by value of a cross section (useful with panel data). These values can then be used in a mixed graph using the "band" option.
Regards,
R
Who is online
Users browsing this forum: No registered users and 14 guests