Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/214945 
Year of Publication: 
2019
Series/Report no.: 
CESifo Working Paper No. 7943
Publisher: 
Center for Economic Studies and ifo Institute (CESifo), Munich
Abstract: 
This paper uses a modelling framework which includes two singularities (or poles) in the spectral density function, one corresponding to the long-run (zero) frequency and the other to the cyclical (non-zero) frequency. The adopted specification is very general, since it allows for fractional integration with stochastic patterns at the zero and cyclical frequencies and includes both long- and short- memory components. The cyclical patterns are modelled using Gegenbauer processes. This model is estimated using monthly data for five European stock market indices (DAX30, FTSE100, CAC40, FTSE MIB40, IBEX35) from January 2009 to January 2019. The results indicate that the series are highly persistent at the long-run frequency, but they are not supportive of the existence of cyclical stochastic structures in the European financial markets. The only clear evidence of a stochastic cycle is obtained in the case of France under the assumption of white noise disturbances; in all other cases, there is no evidence of cycles.
Subjects: 
European stock markets
long run behavior
cycles
persistence
JEL: 
C22
C58
Document Type: 
Working Paper
Appears in Collections:

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.