Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: eivreg - why the reliability ratio has to be higher than R2


From   "Erasmo Giambona" <e.giambona@gmail.com>
To   statalist <statalist@hsphsun2.harvard.edu>
Subject   st: eivreg - why the reliability ratio has to be higher than R2
Date   Fri, 14 Sep 2007 07:15:08 -0400

Dear Statalisters,

I am using eivreg within Stata to obtain error in variable estimates.
The Stata A-J Reference Manual on page 323 clarifies that if the
reliability ratio is lower that the R2 of the regression of the
affected variable on all other variables, then the adjustment is not
possible. I can also see algebraically that this happens because the
inverse of the "corrected" variance-covariance matrix has all zeros in
the row corresponding to the constant term. However, I cannot grasp
the intuition for this. Is there indeed any intuition for this problem
or it is simply an algebraical result?

Any insight on the issue would be appreciated.
Regards,
Erasmo
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index