Hi,
I am trying to use a code I built using EViews 7 in a machine which has EViews 6 and it does not run because of a line which has to do with quantiles. The code is the following
!quantile=0.01
dummy_ymin = error_y<=@quantile(error_y, !quantile)
Could anyone please tell me the right code in EViews 6?
Thanx in advance
Quantile setting EViews 6
Moderators: EViews Gareth, EViews Moderator, EViews Jason, EViews Matt
-
EViews Gareth
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13600
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Quantile setting EViews 6
The following program ran fine for me in EV6:
Code: Select all
create u 100
series error_y = nrnd
series dummy_ymin
!quantile=0.01
dummy_ymin = error_y<=@quantile(error_y, !quantile)
Re: Quantile setting EViews 6
Hi Gareth,
I was typing a reply saying it still doesn't work. However, I just realized the problem was another one and I already solved it.
Thanks for your reply.
PS, on a different subject, I would like to have your opinion on how I could find the steady-state solution of an equation contained in a system without having to do it by hand.
For instance, I have an equation (contained, among several others, in a system)
B = (v0 + v1 * rb - v2 * id - v3 * re) * Vh / pb
and in order to find the steady-state value of the ratio pb*B/Vh, that is, the value of v0, what I do is make the model run once with a value of v0 close to what I believe it to be, then, if the model stops halfway (as it usually does) type "show @meahn(pb_0*B_0/Vh_0)" and use that in another model as the value of v0, and so on. Of course, I do the same for other behavioral equations and it works well. Although, i would like to have that done automatically instead of having to do it by hand. Have you any ideas? I would appreciate your feedback.
I was typing a reply saying it still doesn't work. However, I just realized the problem was another one and I already solved it.
Thanks for your reply.
PS, on a different subject, I would like to have your opinion on how I could find the steady-state solution of an equation contained in a system without having to do it by hand.
For instance, I have an equation (contained, among several others, in a system)
B = (v0 + v1 * rb - v2 * id - v3 * re) * Vh / pb
and in order to find the steady-state value of the ratio pb*B/Vh, that is, the value of v0, what I do is make the model run once with a value of v0 close to what I believe it to be, then, if the model stops halfway (as it usually does) type "show @meahn(pb_0*B_0/Vh_0)" and use that in another model as the value of v0, and so on. Of course, I do the same for other behavioral equations and it works well. Although, i would like to have that done automatically instead of having to do it by hand. Have you any ideas? I would appreciate your feedback.
Who is online
Users browsing this forum: No registered users and 2 guests
