Finite Sample Performance in Cointegration Analysis of Nonlinear Time Series with Long Memory
Afonso Gonçalves da Silva and Peter M Robinson
Published April 2006
Nonlinear functions of multivariate financial time series can exhibit long memory and fractional cointegration. However, tools for analysing these phenomena have principally been justified under assumptions that are invalid in this setting. Determination of asymptotic theory under more plausible assumptions can be complicated and lengthy. We discuss these issues and present a Monte Carlo study, showing that asymptotic theory should not necessarily be expected to provide a good approximation to finite-sample behaviour.
Paper Number EM/2006/501:
Download PDF - Finite Sample Performance in Cointegration Analysis of Nonlinear Time Series with Long Memory
JEL Classification: C32