st: structural break

[Guelmbaye Ngarsandjé <guelmbaye@hotmail.com>]

Hello everybody,

It's me again. As I said I am as new in Stata as
 well as in time series. In order to overcome my difficulties I ordered 
two books which helped me very well (Introduction to time series using 
stata by Sean Becketti and An Introduction to Modern Econometrics Using 
Stata by C. F Baum). However, looking at my tsline of data, my 
supervisor and me suspected structural breaks. I looked for tools to 
identify the points and found the Zandrews test. However, applying the 
test to data and their logs I found two different points (using clemao1)
 with a difference of almost 15 years while clemao2 gives two same break
 points. My questions are:
1 - why clemao1 gives two different points for data in level and for their logs?
2 - Which of the two tests should i use?

Thanks for any help.


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