Gauss-Seidel: Convergence not achieved

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

brisingr90
Posts: 4
Joined: Sun Sep 22, 2013 9:08 am

Gauss-Seidel: Convergence not achieved

Postby brisingr90 » Sun Sep 22, 2013 9:16 am

I am making substitutions using Gauss-Seidel algorithm for 9 equations and I got a message that convergence not achieved. I already recheck my equations and it seems nothing is wrong. Is there anyone can help me solve my problem?

Thank you.

startz
Non-normality and collinearity are NOT problems!
Posts: 3798
Joined: Wed Sep 17, 2008 2:25 pm

Re: Gauss-Seidel: Convergence not achieved

Postby startz » Sun Sep 22, 2013 9:43 am

Try different starting values.

brisingr90
Posts: 4
Joined: Sun Sep 22, 2013 9:08 am

Re: Gauss-Seidel: Convergence not achieved

Postby brisingr90 » Sun Sep 22, 2013 10:35 am

I did. After tried different starting equations, It seems there is one equations that not compatible with another. I am so confused all I can did is 8 equations

brisingr90
Posts: 4
Joined: Sun Sep 22, 2013 9:08 am

Re: Gauss-Seidel: Convergence not achieved

Postby brisingr90 » Sun Sep 22, 2013 1:39 pm

2000 Block 1 - 4 eqns No convergence after 5000 iterations
Solve terminated - Convergence not achieved

anyone know what is wrong?

*2000 is the year. What is the meaning of "Block 1 -4 eqns"?

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13604
Joined: Tue Sep 16, 2008 5:38 pm

Re: Gauss-Seidel: Convergence not achieved

Postby EViews Gareth » Sun Sep 22, 2013 6:36 pm

You're using a model object?


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests