Estimation of Common Long-Memory Components in Cointegrated Systems
Jesús Gonzalo · Cambridge University Press eBooks · 2008
The study of cointegration in large systems requires a reduction of their dimensionality. To achieve this, the authors propose to obtain the I(1) common factors in every subsystem and then analyze cointegration among them. A new way of estimating long-memory components is proposed. The identification of these I(1) common factors is achieved by imposing that they be linear combinations of the original variables X[subscript]t, and that the error correction terms do not cause them at low frequencies. Estimation is done from an error correction model, which makes it possible to test hypotheses on the common factors using standard chi-squared tests. (This abstract was borrowed from another version of this item.)