Dev Vencappa
> I have a small problem within a loop. I have estimated a
> variable using the command dfgls
>
> dfgls variable1
>
> I saved the lag order at the minimum of the MAIC into a scalar
>
> scalar x=r(maiclag)
>
> * and I saved all the statistics into a matrix
>
> matrix y=r(results)
>
> Now I want to be able to retrieve the DFGLS statistic from
> matrix y if the value of the lag k within that matrix
> equals the value of the scalar x and call both into a
> variable that I can see within the data editor
>
> I am not conversent with calling matrix values in stata.
My suggestion is: don't do it this way.
It is not quite painting yourself into
a corner, but it makes life more difficult
than is necessary.
If you want to use your results as if they
were a further dataset, which is natural
and common, set them up so they really
do become a new dataset. Stata matrices
don't really lend themselves to the
kind of thing you want. It is possible,
but you will end up writing lots of
little programs to implement trivial
one-off tasks.
So, starting from where you are, the
best advice might be to get the values
out of that matrix into new variables
with -svmat-.
Nick
[email protected]
*
* 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/
