Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/67823 
Year of Publication: 
2008
Series/Report no.: 
Queen's Economics Department Working Paper No. 1171
Publisher: 
Queen's University, Department of Economics, Kingston (Ontario)
Abstract: 
We consider estimation of the cointegrating relation in the stationary fractional cointegration model. This model has found important application recently, especially in financial economics. Previous research has considered a semiparametric narrow-band least squares (NBLS) estimator in the frequency domain, often under a condition of non-coherence between regressors and errors at the zero frequency. We show that in the absence of this condition, the NBLS estimator is asymptotically biased, and also that the bias can be consistently estimated. Consequently, we introduce a fully modified NBLS estimator which eliminates the bias while still having the same asymptotic variance as the NBLS estimator. We also show that local Whittle estimation of the integration order of the errors can be conducted consistently on the residuals from NBLS regression, whereas the estimator only has the same asymptotic distribution as if the errors were observed under the condition of non-coherence. Furthermore, compared to much previous research, the development of the asymptotic distribution theory is based on a different spectral density representation, which is relevant for multivariate fractionally integrated processes, and the use of this representation is shown to reduce both the asymptotic bias and variance of the narrow-band estimators. We also present simulation evidence and a series of empirical illustrations to demonstrate the feasibility and empirical relevance of our proposed methodology.
Subjects: 
fractional cointegration
frequency domain
fully modified estimation
long memory
semiparametric
JEL: 
C22
Document Type: 
Working Paper

Files in This Item:
File
Size
732.81 kB





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