DCC GARCH positive definiteness

[gemmamc88]

Hi,

I was just wondering if it is possible to impose restrictions on the multivariate DCC GARCH model to ensure positive definiteness? I have tried adding asymmetric effects and robust errors and it doesn't solve the problem, is there anything else I could do?

At the moment some of my alpha1 and beta coefficients are negative in each specification.

Thanks

[TomDoan]

It doesn't sound like you have a problem with positive definiteness---instead, it sounds as if some of your series don't show well-behaved "GARCH" behavior. Have you tried fitting them with univariate GARCH models?

[gemmamc88]

Thanks for your help.

That solved my problem.

I had just had one other question....I am performing the Bai Perron test and I wanted to view the output from the "tests" command in the options where you said in:

* @BaiPerron( options ) depvar start end
* # list of regressors

When I request "tests", it just says:

## OP3. This Instruction Does Not Have An Option TES
>>>>1, minspan=4,TESTS)<<<<

My code is @BaiPerron(maxbreaks=1, minspan=4, TESTS) r57 2003:4 2011:3
# constant
where r57 is my dependent variable. I was just wondering if I have done something wrong here?

Thanks

[TomDoan]

It sounds like you're pulling in a fairly old version of BaiPerron. (TESTS has been part of the procedure for two years). Since it's not of any real interest to other users on the forum, check what version you're running and also see what the setting is for "Procedure Directory" on the Directories tab in the Preferences dialog and e-mail the information to support@estima.com.