Hello, I was running non-linear least squares and I got an overflow.
Since then, all other maximization routines that were estimating other equations (and were working before the overflow) got stuck and I kept on obtaining overflows also in equations that i was able to estimate without any problems.
I guess that the overflow affects the maximization routines overall... so my question is if there is a way to restart the routines in order to get rid of the problem caused by the overflow.
Thank you!
getting out of an overflow
Moderators: EViews Gareth, EViews Moderator
-
- Non-normality and collinearity are NOT problems!
- Posts: 3775
- Joined: Wed Sep 17, 2008 2:25 pm
Re: getting out of an overflow
You probably want to change the starting values (in the C vector).
Re: getting out of an overflow
yes... indeed!
the starting values are those appearing in the vector c?
should I go to the vector c and change one by one the values?
the starting values are those appearing in the vector c?
should I go to the vector c and change one by one the values?
-
- Non-normality and collinearity are NOT problems!
- Posts: 3775
- Joined: Wed Sep 17, 2008 2:25 pm
Re: getting out of an overflow
lukeroom wrote:yes... indeed!
the starting values are those appearing in the vector c?
should I go to the vector c and change one by one the values?
It's very hard to know which starting value is causing the problem. You might want to set them all at values you think are reasonable. If that doesn't work then, yes, experimenting with the values makes sense.
Re: getting out of an overflow
very useful, thank you! Finally I know where starting values are stored.
Who is online
Users browsing this forum: No registered users and 17 guests