Hi,
I am trying to estimate a LSTAR model.
The simplest model specification is
Y = C(1) + C(2)*Y(-1) + (C(3) + C(4)*Y(-1))/(1+EXP(-C(5)*(Y(-1)-C(6))))
and it works.
But when I try to change one variable to:
Y = C(1) + C(2)*Y(-1) + (C(3) + C(4)*Y(-1))/(1+EXP(-C(5)*(regime(-1)-C(6))))
I get the error message "insufficient number of observations". Any ideas what might be the problem?
Also, it wouldn't let me fix the value of c(5) to 2.5....
Any ideas?
Thanks!
:ps. I am using Eviews6
"insufficient number of observations" - LSTAR
Moderators: EViews Gareth, EViews Moderator
"insufficient number of observations" - LSTAR
- Attachments
-
- lstar.wf1
- (87.82 KiB) Downloaded 211 times
-
startz
- Non-normality and collinearity are NOT problems!
- Posts: 3798
- Joined: Wed Sep 17, 2008 2:25 pm
Re: "insufficient number of observations" - LSTAR
Your y variable is all NA.
Who is online
Users browsing this forum: No registered users and 2 guests
