SHAZAM Questions and Answers (Q&A) - RSS feedhttp://community.econometrics.com/questions/SHAZAM Econometrics, Statistics and Analytics Communityen<font color="white">Copyright <b>SHAZAM Analytics, 2018</b></font>Thu, 31 Mar 2011 17:16:31 +0000SUR matrix invertibilityhttp://community.econometrics.com/question/193/sur-matrix-invertibility/Hello!
I have 270 observations and I am trying to solve a system of 33 equations. I get a warning that says "Matrix error... Magnitude below machine precision in row -1581." What does this mean? Is the problem because my machine has 32 bits and I am running into numbers that require more?
If I try to remove an equation at random the system solves.
Thanks!
RitaThu, 31 Mar 2011 16:11:39 +0000http://community.econometrics.com/question/193/sur-matrix-invertibility/Answer by ken for <p>Hello!
I have 270 observations and I am trying to solve a system of 33 equations. I get a warning that says "Matrix error... Magnitude below machine precision in row -1581." What does this mean? Is the problem because my machine has 32 bits and I am running into numbers that require more?</p>
<p>If I try to remove an equation at random the system solves.</p>
<p>Thanks!
Rita</p>
http://community.econometrics.com/question/193/sur-matrix-invertibility/?answer=275#post-id-275If removing one equation solves the problem then your 33 equations might create
A singular matrix.
If this is a system of demand equations then this will happen and one equation
Has to always be deleted Thu, 31 Mar 2011 17:16:31 +0000http://community.econometrics.com/question/193/sur-matrix-invertibility/?answer=275#post-id-275