The I(2) model is defined as a submodel of the general vector autoregressive model, by two reduced rank conditions. The model describes stochastic processes with stationary second difference. A parametrization is suggested which makes likelihood inference feasible. Consistency of the maximum likelihood estimator is proved, and the asymptotic distribution of the maximum likelihood estimator is given. It is shown that the asymptotic distribution is either Gaussian, mixed Gaussian or, in some cases, even more complicated.
Scandinavian Journal of Statistics, 1997, Vol 24, Issue 4, p. 433-462
cointegration; integrated processes; time series analysis; vector autoregressive processes; Faculty of Social Sciences