Abstract
Given the impact of the October 1987 crash pre-empting fears of a deep-seated financial collapse, there is now much scope for assessing its importance quantitatively. In this paper, time series techniques are used to analyse the dynamic linkages and propagation of shocks among five European stock markets. While we do not find any long-run relationship of stock markets over the entire sample ped, evidence is found in support of a unique cointegrating vector over each of the pre- and post-crash samples. Furthermore, the dynamic analysis reveals that the lead-lag relationships changed quite significantly over the sample following the crash.
| Original language | English |
|---|---|
| Pages (from-to) | 81-104 |
| Number of pages | 24 |
| Journal | European Journal of Finance |
| Volume | 10 |
| Issue number | 1 |
| DOIs | |
| State | Published - Feb 2004 |
Bibliographical note
Funding Information:The authors would like to especially thank the editor and two anonymous referees for valuable comments, as well as Soren Johansen, Deane Terrell, Adrian Pagan and Warwick Mckibbin for their very helpful advice and discussions. The usual disclaimer, of course, applies. The second author would like to acknowledge financial support provided through a University of New South Wales Special Research Grant. The views expressed in this manuscript are not necessarily shared by Goldman, Sachs and Co., Goldman Sachs International or any of its affiliated offices.
Keywords
- Cointegration
- Granger temporal causality
- Impulse response function
- Pre/post crash
- Stock price index
- Variance decomposition
- Vector error-correction model
ASJC Scopus subject areas
- Economics, Econometrics and Finance (miscellaneous)