Re: Error output of the switching algorithm
Dear Allin, thanks for your reply.
I just run the script in the command line. The message I obtain there is:
"gretl_cholesky_decomp_solve: rcond = 9.99713e-07 (info = 0)
cholesky decomp failed in update_phi"
Unfortunately, I am not sure how to obtain more debugging information at this stage.
Best,
Artur
2012/7/16 Allin Cottrell
<cottrell-SL7aeOxzxAQ@public.gmane.org>
On Mon, 16 Jul 2012, artur tarassow wrote:
> I am trying to estimate a few restricted VECMs, but the estimation does
> fail quite often using the default switching algorithm. Actually, I just
> would like to know to what exactly does the following error message refer
> to:
>
> "Switching algorithm: failed
> Exact or near collinearity encountered"
>
> I could not find any hints in the C-sources. Are the restrictions collinear
> or is it the high correlation between variables?
inversions, in the switching algorithm. Somewhere along the line
some matrix can't be inverted; and the message you're getting means
that the error code, presumably from a function in gretl_matrix.c,
was E_SINGULAR. Without putting in a lot of debugging statements I
can't say exactly which matrix/function-call combination is
generating the error.
Allin Cottrell
_______________________________________________
Gretl-users mailing list
Gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
http://lists.wfu.edu/mailman/listinfo/gretl-users
<div>
<p>Dear Allin, thanks for your reply.<br><br>I just run the script in the command line. The message I obtain there is:<br><br>"gretl_cholesky_decomp_solve: rcond = 9.99713e-07 (info = 0)<br>cholesky decomp failed in update_phi"<br><br>Unfortunately, I am not sure how to obtain more debugging information at this stage.<br><br>Best,<br>Artur<br><br></p>
<div class="gmail_quote">2012/7/16 Allin Cottrell <span dir="ltr"><<a href="mailto:cottrell@...u" target="_blank">cottrell@...</a>></span><br><blockquote class="gmail_quote">
<div class="HOEnZb"><div class="h5">On Mon, 16 Jul 2012, artur tarassow wrote:<br><br>
> I am trying to estimate a few restricted VECMs, but the estimation does<br>
> fail quite often using the default switching algorithm. Actually, I just<br>
> would like to know to what exactly does the following error message refer<br>
> to:<br>
><br>
> "Switching algorithm: failed<br>
> Exact or near collinearity encountered"<br>
><br>
> I could not find any hints in the C-sources. Are the restrictions collinear<br>
> or is it the high correlation between variables?<br><br>
</div></div>There's a huge amount of matrix computation, including lots of<br>
inversions, in the switching algorithm. Somewhere along the line<br>
some matrix can't be inverted; and the message you're getting means<br>
that the error code, presumably from a function in gretl_matrix.c,<br>
was E_SINGULAR. Without putting in a lot of debugging statements I<br>
can't say exactly which matrix/function-call combination is<br>
generating the error.<br><br>
Allin Cottrell<br><br>
_______________________________________________<br>
Gretl-users mailing list<br><a href="mailto:Gretl-users@...">Gretl-users@...</a><br><a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br>
</blockquote>
</div>
<br>
</div>
RSS Feed