Hi All,
I am working with time series data which has a dependent variable I(2) { Stationary at second order difference} and other independent variables are stationary at I(1).
Also, there exists cointegration between these variables.
I want to know whether I can run the VECM process with I(2) Dependent variable and I(1) Independent variables.?
Please advise possible options that I can follow.
Thank you.
The VECM like the VAR requires that the variables are intergrated of order 1 and not order 2.
So to solve the problem, i would advise the following;
1. Use the Toda-Yamamoto Non-granger causality test. The Toda-Yamamoto can be used regardless of the order of integration.
2. IF you want to run the VECM, then try to Transform the variables into logs. Logartihmic transformation can assist with statitionarity of the variables.
3. If your study period is too long, try reducing it within acceptable means. A longer study period affects stationarity of the variables due to changes in regime and because of structural breaks. Time series variable can have a constant mean, variance and covariance for a certain period of time.
Thank you
In time series co integration modelling, variables which are being stationary at second order are not included. The second order integrated variable will create the interpretation issues because the usually the hyper growths in the variables leads the disturbances of the data which are caused due to conflict, regional changes, structural changes.
Solution: Transform your data variables (not only one variables which order=2) into meaningful economic interpretation. Normalize the index variables with its base (if you are using), reduce the sample size but up to that level which is acceptable for time series analysis.
Hi Welani Khondowe Muhammad Kazim Jafri ,
Thank you for your responses. I reduced my sample data points and tried again. Because my dataset included data from the covid 19 period. So I removed covid 19 affected period from my dataset and run the unit root again. Then all the log forms of variables were stationary at level 1 (I1).
Thank you both of you very much.
Cheers!!!
- Badges
- Science topic
- Similar topics
- Indexes