In the six years since I completed the manuscript for the first edition of The Econometric Modelling of Financial Time Series, there have been many advances in time series econometrics, some of which have been in direct response to features found in the data coming from financial markets, while others have found ready application in financial fields. Incorporating these developments, and omitting some techniques that have since fallen out of favour, has led to a second edition rather different to the first. Although the basic structure of the book remains the same, it is worth pointing out these changes in some detail.

Chapters 1 and 2 remain essentially the same, although examples have been updated. It is in chapter 3 that the first major changes appear. Like it or not, the analysis of unit roots has come to dominate much of time series econometrics during the 1990s. Although much of the recent published research on unit roots has been highly technical without being particularly illuminating, I felt that a more formal analysis of unit root testing and inference than appeared in the first edition was warranted. To this end, there is now a more detailed treatment of the asymptotic distributions of the various test statistics and an emphasis on Monte Carlo simulation to obtain estimates of these distributions and hence critical values. Newer developments incorporating breaking and evolving trends and stochastic unit roots are also discussed. This chapter also includes a rather more detailed treatment of fractionally integrated processes.