Re: [R] ols/gls or systemfit (OLS, WLS, SUR) give identical results

From: Mihai Nica <>
Date: Tue 18 Jul 2006 - 03:06:11 EST

  I should have not send the post to the list, and I apologize. The problem was on my part, and easily solvable. Thanks for your concern, I really appreciate it, and thanks to the list for patience. This is really a great resource and should not be abused :-)   mihai

Spencer Graves <> wrote: I can't say without more information. If the system were saturated (i.e., has as many equations as unknowns), you should get the same answer from all the different methods. However, I just tried a saturated model in 'systemfit', with the following results:

 > DF2 <- data.frame(y=1:2, x=3:4)
 > lm(y~x, DF2)
lm(formula = y ~ x, data = DF2)


(Intercept)            x
          -2            1

 > library(systemfit)
 > systemfit("OLS", list(eqn=y~x), data=DF2) Error in solve.default(sigma, tol = solvetol) :  system is computationally singular: reciprocal condition number = 0  >
   If you'd like more help from this listserve, please supply a simple, self-contained example to illustrate your question (as suggested in the posting guide! "").

   Hope this helps.
   Spencer Graves

Mihai Nica wrote:
> I might be sorry for asking this question :-)
> I have two equations and I tried to estimate
them individually with "lm" and "gls", and then in a system (using systemfit) with "OLS", "WLS" and "SUR". Quite surprisingly (for myself at least) the results are identical to the last digit.
> Could someone (please!) give a hint as to what
am I doing wrong?
> Thanks,
> mihai
> ---------------------------------
> [[alternative HTML version deleted]]
> ______________________________________________
> mailing list
> PLEASE do read the posting guide!

See the all-new, redesigned Check it out.

        [[alternative HTML version deleted]] mailing list PLEASE do read the posting guide! Received on Tue Jul 18 04:36:07 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Tue 18 Jul 2006 - 06:16:24 EST.

Mailing list information is available at Please read the posting guide before posting to the list.