I am using Stata13, and have a time series data (no. of obs = 35) and I'm testing the relationship between y and x. Every thing is going well as in - both series are I(1) and are cointegrated. However, in applying the ECM, the ECM coefficient is both positive and statistically insignificant an indication that both variables may not converge in the long-run. I decided to test for structural breaks in the data and I used these codes which I obtained from Stata14 website:
estat sbsingle and estat sbknown after running my regression.
Both codes turned out to be invalid in Stata13. Can someone please help me out on the applicable codes or on how best to manoeuvre this problem.
Thank you.
Ngozi
Hi Ngozi,
Both of these commands have only been introduced in Stata version 14, thus you won't be able to run them in an earlier version of the software. There are some user-written programs that you can consider though, such as clemao_io, ghansen, qll, and zandrews
All these programs can be downloaded into Stata by typing: ssc install program (where program is the name of the program)
I hope this helps
Ariel
Hi Ngozi,
Both of these commands have only been introduced in Stata version 14, thus you won't be able to run them in an earlier version of the software. There are some user-written programs that you can consider though, such as clemao_io, ghansen, qll, and zandrews
All these programs can be downloaded into Stata by typing: ssc install program (where program is the name of the program)
I hope this helps
Ariel
thanks Ariel....you just made my day!....I'll try the codes and revert on my results....thanks a lot!
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Regression