STATISTICAL ANALYSIS

Tests of Random Walk Hypothesis



Tests of Random Walk Hypothesis

Introduction

The study is related to the of efficient market hypothesis, weak form efficiency, random walk hypothesis and the types of random walk hypothesis. The efficient market hypothesis is a concern which is a well documented and studied concepy in economics. There is widespread controversy and disagreement on efficient market hypothesis as according to some investors and economists, one can beat the market by building mathematical models and by mathematical trading. In the view of few investors, by using the technical analysis, an individual can forecast the price of stocks. In this context, the weak form efficiency of market include the price of an asset entails all historical or past financial information about that stocks. In order words, market efficiency hypothesis (EMH) states that the stock returns are uncorrelated and have a constant mean. In the same way, a market is measured as the weak form efficient, if the current prices reflects all information contained in the past prices that implies that no investor can plan a trading rule based exclusively on the histirical price patterns to get abnormal returns.

Besides it, the random walk hypothesis implies that the price of securities as a random process behavior. It is normally to distributed price changes, a zero expectation value for the distribution of price changes; independent price change as well as non-existent encyclical fluctuations and long term trends expected components. The random walk is an immediate consequence of the efficient markets theory. The random-walk theory and the theory of symmetric random walk describe the time course of market prices (especially stock prices and other securities prices) mathematically. The theory of random walks is the theory that changes in the value of securities fluctuate randomly around its objective price, opposes the theory of technical analysis. In its most general form, random walks are any random process where the position of a particle at a certain instant depends only on its position at some instant before and some random variable that determines its subsequent direction and step length.

Literature Review

The model of random walk hypothesis was developed by Bachelier (1900) who particularly focused on the consecutive changes in the price within two periods is not dependent with the variance is related with the interval between the two time periods and the mean is zero. In relation to this, the variance of changes that occur weekly should be five times greater than the variance of the changes that takes place daily with the assumption that the markets keep closed on weekends (Campbell, Lo and MacKinlay, 1997, 18-52). The phenomenon is found in the variance ratio test that has been extensively employed to test the random walk-hypothesis in many markets (Fama, 1970, 383-417). The rejection of the random walk hypothesis in prices of share because of mean changing propensity that is a end result of persistence of one sided volley in the price of shares (Fama, 1991, 1575-1618). Besides it, the Q statistic allows the researcher to test the ...