VECM in cointegration analysis: How to chose the form of the deterministic terms from dataplots

by k.dkhk   Last Updated August 13, 2019 21:19 PM

Please have a look at the plot of 5 different time series $Y_t=(y_{1,t},y_{2,t},y_{3,t},y_{4,t},y_{5,t})$. I want to use R's urca package to perform cointegration analysis on $Y_t$ using the VECM (vector error corrected model): $$ Y_t = \Pi Y_{t-1} + \sum_{i=1}^k\Gamma_i\Delta Y_{t-i}+\Phi D_t +\epsilon_t $$

  • How should I determine the form of the VECM regarding the deterministic term?

  • Can I by "eyeball" method make a reasonable decision?

The 3 most common ways are implemented in urcaas: trend = none,const drift.

I am using these books:

  • Analysis of Integrated and Cointegrated Time Series with R by Pfaff
  • New Introduction to Multiple Time Series Analysis by L├╝tkepohl

Neither of these books say anything about this topic but in there examples (I think) they use the "eyeball" methodenter image description here



Related Questions





Dummy variables in Johansen cointegration analysis

Updated February 02, 2019 04:19 AM