This article applies autoregression and rescaled range statistics to very long stock market series to test the hypothesis that long-term temporal dependencies are present in financial data. For the annual capital appreciation returns to the London Stock Exchange, evidence of persistence in raw returns greater than 5 years and of mean reversion in deviations from rolling 20-year averages is found. Similar patterns are observed for the NewYork Stock Exchange; however, they are not significant at traditional confidence levels.