Optimal and adaptive semi-parametric narrowband and broadband and maximum likelihood estimation of the long-memory parameter for real exchange rates

Heravi, Saeed ORCID: https://orcid.org/0000-0002-0198-764X and Patterson, Kerry 2005. Optimal and adaptive semi-parametric narrowband and broadband and maximum likelihood estimation of the long-memory parameter for real exchange rates. The Manchester School 73 (2) , pp. 165-213. 10.1111/j.1467-9957.2005.00441.x

Full text not available from this repository.

Abstract

The nature of the time series properties of real exchange rates remains a contentious issue primarily because of the implications for purchasing power parity. In particular are real exchange rates best characterized as stationary and non-persistent; nonstationary but non-persistent; or nonstationary and persistent? Most assessments of this issue use the I(0)/I(1) paradigm, which only allows the first and last of these options. In contrast, in the I(d) paradigm, d fractional, all three are possible, with the crucial parameter d determining the long-run properties of the process. This study includes estimation of d by three methods of semi-parametric estimation in the frequency domain, using both local and global (Fourier) frequency estimation, and maximum likelihood estimation of ARFIMA models in the time domain. We give a transparent assessment of the key selection parameters in each method, particularly estimation of the truncation parameters for the semi-parametric methods. Two other important developments are also included. We implement Tanaka's locally best invariant parametric tests based on maximum likelihood estimation of the long-memory parameter and include a recent extension of the Dickey–Fuller approach, referred to as fractional Dickey–Fuller (FD-F), to fractionally integrated series, which allows a much wider range of generating processes under the alternative hypothesis. With this more general approach, we find very little evidence of stationarity for 10 real exchange rates for developed countries and some very limited evidence of nonstationarity but non-persistence, and none of the FD-F tests leads to rejection of the null of a unit root.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Business (Including Economics)
Subjects:	H Social Sciences > H Social Sciences (General) H Social Sciences > HB Economic Theory H Social Sciences > HD Industries. Land use. Labor H Social Sciences > HG Finance
Publisher:	Wiley
ISSN:	1463-6786
Last Modified:	21 Oct 2022 09:56
URI:	https://orca.cardiff.ac.uk/id/eprint/38405

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item