Modelling Political Popularity: An Analysis of Long Range Dependence in Opinion Poll Series by David Byers James Davidson (Cardiff Business School) and David Peel (University of Liverpool) Revised, December 1996 Summary A simple model of political popularity, as recorded by opinion polls of voting intentions, is proposed. We show that, as a consequence of aggregating heterogeneous poll responses under certain assumptions about the evolution of individual opinion, the time series of poll data should exhibit long memory characteristics. In an analysis of the monthly Gallup data on party support in the UK, we confirm that the series are long memory, and further show them to be virtually pure ‘fractional noise’ processes. An explanation of the latter result is offered. We study the role of economic indicators in predicting swings in support, perform event analyses, and use our estimates to generate post-sample forecasts to April 1997. Keywords: Political popularity, opinion polls, long memory, fractionally integrated processes Address for correspondence: James Davidson, Cardiff Business School, Colum Drive, Cardiff CF1 3EU email: DavidsonJE@cardiff.ac.uk