Technical analysis and the stochastic properties of stock returns

Abstract

Technical analysis is the heading of numerous trading techniques. Technical analysts attempt to forecast prices by the study of past prices and through the years, have invented hundreds of indicators, some of which have proved to be objective, reliable and useful. The simplest and most common technical rules are examined in this paper, the moving average oscillator and the trading range breakout, by utilizing the General Index of the Athens Stock Exchange from1985 to 2009. These rules create buy and sell signals under specific conditions. If technical analysis didn’t have any power to forecast price movements, then the returns observed on days when the rules produce buy signals wouldn’t differ appreciably from returns on days when the rules produce sell signals. The profits from this procedure are calculated by adopting the framework of “double or out” strategy. For any stock it is 50% likely to go up tomorrow, and 50% to fall. It's comic to think that using any method can predict the movement of financial markets with precision. Only probabilistic can be expressed the next day. If technical analysis aims somewhere, this is to change these rates of fortune for the benefit of the investor. If we have 60% chance to correctly predict the movement of a share, sooner or later will win money from it. The results of this paper provide strong support for the technical strategies examined. Through the bootstrap method, is reached the conclusion that the returns obtained from these strategies are not consistent with the GARCH (1, 1) model. Buy signals consistently generate higher returns than sell signals and the returns following buy signals are less volatile than returns following sell signals. Furthermore, returns following sell signals are negative, which is not easily explained by any of the current equilibrium models.