Testing for a Long Run Relationship between Trend and Difference Stationary Series
The theory of cointegration and error correction models developed in the last couple of years by, among others, Engle and Granger (1987), as well as Johansen (1988) proved very useful for testing and estimating long-run relationships between difference stationary [I(1)] series. However, there is an increasing literature expressing the view that the autocorrelation of macroeconomic time series could be produced either by trend or difference stationary models [e.g. Christiano Eichenbaum (1990) and the evidence presented by stock (1991)]. Of course, the idea of co integration cannot be applied to trend stationary series, but there is the related idea of codependence suggested by Gourieroux and PeaucelIe (1989) which is designed for testing a long run relationship between stationary series. This paper uses this approach in a VAR framework which can be applied to trend and difference stationary variables.
Unable to display preview. Download preview PDF.
- Gourieroux, C. and I. Peaucelle (1989) Detecting a Long Run Relationship (With an application to the P.P.P. Hypothesis). CEPREMAP, working Paper N-8902.Google Scholar
- Kugler, P. and K, Neusser (1992) International Real Interest Rate Equalization: A Multivariate Time Series Approach, under revision Journal of Applied Econometrics.Google Scholar
- Kugler, P. and P. Schwendener (1991) Codependence in a VAR Framework, paper presented at the European Meeting of the Econometric Society, Cambridge, September 2–6, 1991.Google Scholar