Long-run Relations in a Well Defined Statistical Model for the Data Generating Process. Cointegration Analysis of the PPP and the UIP Relations
The concept of a well defined statistical model for the data generating process is given an empirical formulation in the vector autoregressive model under assumption of cointegration in an analysis of prices, interest rates and exchange rates between Denmark and Germany. The long-run relations are estimated as stationary linear combinations between the non-stationary variables and the presence of deterministic components in the common stochastic trends is investigated. Structural hypothesis on the purchasing power parity and uncovered interest rate hypothesis are tested in a full information maximum likelihood framework. Empirical support for both of these fundamental relations are found. Comparative analysis of the long-run relations based on the single equation ecm-model as well as the Engle-Granger two-step procedure are performed. The full system versus the partial system analysis approach is discussed in terms of optimal inference on the long-run parameters. By testing hypotheses on the weight coefficients it is empirically demonstrated that the full five-dimensional system cannot be reduced without loosing some efficiency.
To our knowledge, this item is not available for
download. To find whether it is available, there are three
1. Check below under "Related research" whether another version of this item is available online.
2. Check on the provider's web page whether it is in fact available.
3. Perform a search for a similarly titled item that would be available.
|Date of creation:||May 1990|
|Date of revision:|
|Contact details of provider:|| Postal: |
Phone: (+45) 35 32 30 10
Fax: +45 35 32 30 00
Web page: http://www.econ.ku.dk
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:kud:kuiedp:9011. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Thomas Hoffmann)
If references are entirely missing, you can add them using this form.