Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/62810
Authors: 
Baillie, Richard
Kapetanios, George
Year of Publication: 
2005
Series/Report no.: 
Working Paper, Department of Economics, Queen Mary, University of London 528
Abstract: 
This paper constructs tests for the presence of nonlinearity of unknown form in addition to a fractionally integrated, long memory component in a time series process. The tests are based on artificial neural network structures and do not restrict the parametric form of the nonlinearity. The tests only require a consistent estimate of the long memory parameter. Some theoretical results for the new tests are obtained and detailed simulation evidence is also presented on the power of the tests. The new methodology is then applied to a wide variety of economic and financial time series.
Subjects: 
Long memory, Non-linearity, Artificial neural networks, Realized volatility, Absolute returns, Real exchange rates, Unemployment
JEL: 
C22
C12
F31
Document Type: 
Working Paper

Files in This Item:
File
Size
347.67 kB





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