Exploring Dual Long Memory in Returns and Volatility Across Central and Eastern Europe Stock Markets
We investigate the presence of long memory in emerging CEE stock markets using the nonparametric, semiparametric and parametric approaches. We consider the methodology of Bai and Peron to test for structural breaks in the return series and we perform tests of fractionally integrated process on subsamples in order to identify potential evidence of spurious long memory. We test for long memory in both conditional mean and conditional variance by combining a fractionally integrated regression function and a fractionally integrated skedastic function.We estimate ARFIMA-GARCH and ARFIMA-FIGARCH models under two proposed distributions. The skewed Student-t distribution is found to better describe the data comparing to Gaussian distribution. We conclude that the Romanian, Hungarian and Czech Republic capital markets show evidence of dual long memory in returns and volatility, while the Bulgarian and Poland markets show strong features of long memory in volatility, but no long memory in the return series.
|Date of creation:||Nov 2009|
|Date of revision:|
|Contact details of provider:|| Postal: 6 ROMANA PLACE, 70167 - BUCHAREST|
Web page: http://www.dofin.ase.ro/carfib/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:cab:wpaefr:40. 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: (Ciprian Necula)
If references are entirely missing, you can add them using this form.