Fractional integration methods in political science

We argue that fractional integration methods have the potential to unify and simplify time series analysis. Estimation of the d parameter in an ARFIMA (p, d, q) model is no longer difficult and multivariate extensions are proving useful. In particular, we discuss and illustrate the most promising route, fractional cointegration and the innovation of relaxing the assumption that the parent series are I(1). We illustrate the technique with an analysis of congressional approval, a topic of great interest to institutional scholars, and its relationship with economic expectations. (C) 1999 Elsevier Science Ltd. AU rights reserved.