baiperron test

Discussion of models with structural breaks or endogenous switching.

baiperron test

Postby prakash » Tue Sep 02, 2008 11:07 pm

Hello sir, I have one query related to test of structural break developed Bai and perron together. could you let me know what "list of regressors" means in your RATS programming of the test. basically I am testing the possible presence of structural break in the state domestic product data series. Waiting for your reply
Prakash Singh
Senior research Analyst
Institute of Economic Growth
New Delhi, India
prakash
 
Posts: 6
Joined: Tue Sep 02, 2008 7:09 am

Re: baiperron test

Postby TomDoan » Wed Sep 03, 2008 9:41 am

prakash wrote:Hello sir, I have one query related to test of structural break developed Bai and perron together. could you let me know what "list of regressors" means in your RATS programming of the test. basically I am testing the possible presence of structural break in the state domestic product data series. Waiting for your reply


BaiPerron is an efficient method for finding optimal break points in a linear regression y(t)=X(t)b+u(t). The "list of regressors" are the X variables. If the domestic product is actually your "y" series, then Bai-Perron may not be what you want. For instance, if your interest is in broken trends in log GDP, Bai-Perron can handle only certain types of those - either a complete break with both intercept and trend rate changing, or (using the NFIX option) a fixed trend rate, but with breaks in the intercept. It can't handle a spline situation where the trend rate changes but the function value doesn't.
TomDoan
 
Posts: 2720
Joined: Wed Nov 01, 2006 5:36 pm

Bai Perron test

Postby prakash » Wed Sep 03, 2008 11:17 pm

with regard to your reply of my query about Bai Perron test, I am basically checking the same but in place of national GDP it is State Domestic product, which I have taken in log form ie Log SDP and in that I am interested in finding whether there is any structural break or not. additionaly as you have mentioned about fixing the trend rate: do I need to give NFIX a numeric value or I have something else.

Thanks
Prakash Singh
Senior research Analyst
Institute of Economic Growth
New Delhi, India
prakash
 
Posts: 6
Joined: Tue Sep 02, 2008 7:09 am


Return to Structural Breaks and Switching Models

Who is online

Users browsing this forum: No registered users and 1 guest

cron