I don't have timberlake package to estimate an ARDL model I am using TSP So I am doing a two step procedure(unit root for number of lags and ols). Can somebody tell me how to calculate the right t-statistics?.
You have to run a UECM and obtain the long-run parameters, that is by dividing through using the coefficient on the one-period lagged level of the dependent variable, then use these obtained long-run coefficients to create an ECM term. Remember not the Engle and Granger residuals. Then reestimate the UECM using the same lagged structure identified by AIC earlier.
Hi, is there a way to estimate two ARDL equations in a system? I am thinking of estimating two UECM form of equations in a system, but i wonder whether it makes sense. Thanks for your comments.