Optimal lags and Error-correction model

[Pita Fouta]

Good morning everyone;

I want to perform a cointegration with the Error correction model.

Everything works fine. My data with optimal lags 1 and 2 are of the same order I(1).

They are stationary in the first difference.

However here is my code to determine if, in the first difference, they are stationary:

varsoc dloga
* Optimal lag = 2 by HQIC, SBIC, AIC
varsoc dlogb
* Optimal lag = 0 by HQIC, SBIC, AIC

As you can see the optimal lag for the first difference of the second variable b is 0 with all criteria. I wanted to know if this would be a problem later in the estimation of my coefficients for the error correction model.

Thanks in advance.

Pita

[Sebastian Kripfganz]

I do not see any reason why this should be a problem. You can estimate the error-correction model with the community-contributed ardl command. This command automatically determines the optimal lag orders. The varsoc command is not needed.

• Kripfganz, S. and D. C. Schneider (2018). ardl: Estimating autoregressive distributed lag and equilibrium correction models. Proceedings of the 2018 London Stata Conference.
• ARDL: updated Stata command for the estimation of autoregressive distributed lag and error correction models