Regression Theory for Near-Integrated Time Series.
The concept of a near-integrated vector random process is introduce d, helping the author work towards a general asymptotic theory of regression fo r multiple time series in which some series may be integrated processe s of the ARIMA type, others may be stable ARMA processes with near unit roots, and yet others may be mildly explosive. A limit theory for th e sample moments of such time series is developed using weak convergence. The theory is applied to the study of vector autoregress ions and cointegrating regressions of the type advanced by R. F. Engle and C. W. Granger (1987). A noncentral limiting distribution theory is derived for some recently-proposed multivariate unit root tests. Models with drift and near-integration are also studied. Copyright 1988 by The Econometric Society.
Year of publication: |
1988
|
---|---|
Authors: | Phillips, Peter C B |
Published in: |
Econometrica. - Econometric Society. - Vol. 56.1988, 5, p. 1021-43
|
Publisher: |
Econometric Society |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Maximum Likelihood Estimation in Panels with Incidental Trends.
Moon, Hyungsik R, (1999)
-
The Exact Distribution of LIML: II.
Phillips, Peter C B, (1985)
-
Phillips, Peter C B, (1994)
- More ...