Predicting Daily Stock Returns: A Lengthy Study of the Hong Kong and Tokyo Stock Exchanges

Abstract

If stock markets are efficient then it should not be possible to predict stock returns, i.e.,_x000D_ no explanatory variable in a stock market regression model should be statistically_x000D_ significant. In this study, we find results indicating that daily effects exist in stock market returns. These daily or calendar effects previously shown to exist by others clearly indicate the purpose of this study. Researchers often equate stock market efficiency with the nonpredictability property of time series of stock returns. We explore whether this line of_x000D_ argument is satisfactory and aids in furthering our understanding of how markets operate._x000D_ We focus on one definition of capital market efficiency and on the experience of these_x000D_ principles in analyzing the performance of Hong Kong and Tokyo stock exchanges. We observe that stock returns (which include closing prices and dividends) are predictable and there are explanations for short-term predictability. Hong Kong and Japan are the focus of this study because of the maturity of their financial markets and the availability of clean data on these markets from a reputable and available source.