It is well known that unit root limit distributions are sensitive to initial conditions in the distant past. If the distant past initialization is extended to the inﬁnite past, the initial condition dominates the limit theory producing a faster rate of convergence, a limiting Cauchy distribution for the least squares coeﬀicient and a limit normal distribution for the t ratio. This amounts to the tail of the unit root process wagging the dog of the unit root limit theory. These simple results apply in the case of a univariate autoregression with no intercept. The limit theory for vector unit root regression and cointegrating regression is aﬀected but is no longer dominated by inﬁnite past initializations. The latter contribute to the limiting distribution of the least squares estimator and produce a singularity in the limit theory, but do not change the principal rate of convergence. Usual cointegrating regression theory and inference continues to hold in spite of the degeneracy in the limit theory and is therefore robust to initial conditions that extend to the inﬁnite past.
Phillips, Peter C.B. and Magdalinos, Tassos, "Unit Root and Cointegrating Limit Theory When Initialization Is in the Infinite Past" (2008). Cowles Foundation Discussion Papers. 1959.