Hi all,

First of all, I apologise if this is a very basic question: I have just started learning econometrics and STATA. However, I wasn't able to find answers elsewhere, so I hope that somebody will be able to lend guidance here.

I am trying to fit a model on the volatility of S&P 500 and see if structural breaks can be identified around times of economic or political turmoil. After reading up on it, I have come to understand that GARCH(1,1) models are the standard for volatility modeling. However, I would like to add exogenous regressors to the conditional variance regression: for instance dummies for times of economic uncertainty but also other contols. Ie something on form:
y_t = \epsilon_t
\sigma_T^2 = c + b_1 \epsilon_t-1^2 + b_2 \sigma_t-1^2 + b_3 dummy + b_4 x

How can I do this in STATA? I have looked up the "arch" command documentation, but all I can find in terms of exogenous variables is the "het(varlist)" option, which (if I understand it correctly) adds the variables are a multiplicative exponential. Is there a way to get them linear?

Also, is there any structural break test built into STATA which can be used with arch? The dummy variable solution I feel is not ideal, but estat sbknown and it's peers don't work with it.

Many thanks!

Alex