I am using Eviews 7.1.
I try to estimate a three dimensional (i,j,t) panel model with time-varying fixed effects for i and j (e.g. country-code x time). The size of the panel is about 180 (i), 180 (j) and 45 (t), so there are 16200 'it' and 16200 'jt' dummy variables. When I try to estimate the model, I get the 'Out of memory' error message. Does this mean that my computer/processor is not good enough, or Eviews has an internal limit for the number of independent variables in an equation?
Thanks for your help.
Laszlo
Eviews limits
Moderators: EViews Gareth, EViews Moderator
-
EViews Gareth
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13585
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Eviews limits
You've hit the limits of your computer / operating system.
Getting more memory and/or switching to a 64bit operating system may help.
Getting more memory and/or switching to a 64bit operating system may help.
Re: Eviews limits
Thanks Gareth, I'll buy a new laptop.
Just one more thing. This morning I tried to set up my panel data as a dated panel with a dateid and two-dimensional (it, jt) cross-section identifier. It did not work because dateid was nested in the in the other dimension of the panel structure. Hence, I tried to set up an undated panel instead, but this time Eviews wanted to insert 40,996,744(!) new observations in the workfile.
Laszlo
Just one more thing. This morning I tried to set up my panel data as a dated panel with a dateid and two-dimensional (it, jt) cross-section identifier. It did not work because dateid was nested in the in the other dimension of the panel structure. Hence, I tried to set up an undated panel instead, but this time Eviews wanted to insert 40,996,744(!) new observations in the workfile.
Laszlo
Who is online
Users browsing this forum: No registered users and 2 guests
