We empirically investigated the relationships between the degree ofefficiency and the predictability in financial time-series data. The Hurstexponent was used as the measurement of the degree of efficiency, and the hitrate calculated from the nearest-neighbor prediction method was used for theprediction of the directions of future price changes. We used 60 market indexesof various countries. We empirically discovered that the relationship betweenthe degree of efficiency (the Hurst exponent) and the predictability (the hitrate) is strongly positive. That is, a market index with a higher Hurstexponent tends to have a higher hit rate. These results suggested that theHurst exponent is useful for predicting future price changes. Furthermore, wealso discovered that the Hurst exponent and the hit rate are useful asstandards that can distinguish emerging capital markets from mature capitalmarkets.
展开▼