| Author(s): |
prof. PhDr. Ladislav Krištoufek Ph.D.,
|
| Type: |
Articles in journals with impact factor |
| Year: |
2016 |
| Number: |
0 |
| ISSN / ISBN: |
|
| Published in: |
Acta Physica Polonica A 129(5), pp. 908-912 PDF |
| Publishing place: |
|
| Keywords: |
|
| JEL codes: |
|
| Suggested Citation: |
|
| Grants: |
GAČR 14-11402P Bivariate long memory analysis of financial time series (2014-2016)
|
| Abstract: |
We propose two novel methodological approaches -- the detrending moving average based regression coefficient estimator and the scale-dependent instrumental variable estimator -- and show their utility on a specific case of dependence between stock markets and connected foreign exchange rates in the Central European region -- the Czech Republic, Hungary and Poland. The methodology has proven useful as we uncovered several interesting findings such as scale dependence of the shock transmission and differences between the Euro and U.S. dollar currency pairs. The Polish currency is also the most sensitive of the three with respect to the stock market shocks. The proposed methodology can be applied to any system with potential endogeneity issues if one is interested in the scale variability of the effect of interest. |
