Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: Inequality constraints for ARCH/GARCH


From   Martien Lamers <Martien.Lamers@ugent.be>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Inequality constraints for ARCH/GARCH
Date   Fri, 1 Apr 2011 09:03:13 +0200

Dear Anton,

I completely agree with you. Although some people may point to this FAQ: http://www.stata.com/support/faqs/stat/intconst.html
It does have solutions to the problem of inequality constraints, but personally I think they're quite cumbersome. I wrote a ML program of more or less 300 lines long, which I wanted to fit to 11 different time series. The problem is that each time series had to have different inequality constraints. So instead of writing 1 ML program and using moptimize (or ml model) with different inequality constraint matrices, I had to write 11 different programs (3300 lines), 11 different nlcom commands, each with their own constraints.

 Although I do not have experience with it, I don't think that it should be that difficult to develop inequality constraints. GAUSS, MATLAB and I think R have the inequality matrices/constraints, but the reason many of us use Stata is to combine the great data management tools with Constrained ML. In the end I did get everything to work, but I think that there should be an easier way for this. 

Martien

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Anton Granik
Sent: vrijdag 1 april 2011 8:38
To: statalist@hsphsun2.harvard.edu
Subject: st: Inequality constraints for ARCH/GARCH

Dear all,

I found that this issue was discussed here back in 2004....we are in 2011 now My question is why is it so hard for STATA creators to allow for an easy introduction of inequality constraints? In estimating volatility models it is particularly important as the unconstrained optimization produces meaningless results.

Thank you,

Anton

---------------------
Anton I. Granik
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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   |   Site index