showed that moving average technical trading rules had
some predictive abilities in both conditional means and variances. Further, they showed that these results
were relatively stable over their 90 year sample period. Recently Sullivan, Timmerman & White (1999)
demonstrated that while it appears unlikely that these rules were “snooped” from the earlier sample, their
forecasting performance over recent years has disappeared. This important result raises many serious questions
about trading rules, and the stationarity of financial time series. This paper further explores the
performance of these rules and compares the previous 10 years to the rest of the century. When analyzed in
light of moving average trading rules, some very interesting similarities and differences appear.
This paper corroborates and extends the results in Sullivan et al. (1999). First, analysis is performed on
conditional variances as well as conditional means. Secondly, some further robustness checks are performed,
along with some comparisons with other rules. Specifically, a simpler momentum based dynamic strategy
appears to be very similar to the moving average rules.