Trends and Calendar Effects in Stock Returns

This paper presents statistical investigations regarding the value of the trend concept and calendar effects for prediction of stock returns. The examined data covers 207 stocks on the Swedish stock market for the time period 1987-1996. The results show a very weak trend behavior. The massive better part of returns falls into a region, where it is very difficult to claim any correlation between past and future price trends. It is also shown that seasonal variables, such as the month of the year, affect the stock returns more than the average daily returns. This is consequential for all methods, where the seasonal variables are not taken into account in predicting daily stock returns.