This paper aims to examine the existence of calendar anomalies including month-of-year effect, turn-of-month effect, and weekend effect in Thai stock market. The stock return is computed from SET index during 1988 to ...This paper aims to examine the existence of calendar anomalies including month-of-year effect, turn-of-month effect, and weekend effect in Thai stock market. The stock return is computed from SET index during 1988 to 2009 and the SET50 index gathered since it was created in 1995. The unit root test is performed to ensure that the stock return series have no unit root. The multiple regression techniques using dummy variables are employed to test the difference of the return during each calendar anomalies period. If the regression model suffers from conditional heteroskedasticity, the GARCH （1, 1） model will be used instead of normal ordinary least square regression. It was found that the calendar anomalies exist in Thai stock market. The return is abnormally high during December and January, which can be addressed to be the turn-of-year effect. The return during the turn-of-month period, which can be defined as the last trading day and the first four trading days of the following months, is also abnormally high. Finally, the return is also abnormally high on Fridays but abnormally low on Mondays, which is addressed as weekend effect. This may create the opportunity to make above-average profit to investors exploiting these calendar anomalies. Although these calendar anomalies may be difficult to be exploited in practice because of transaction costs and ability to replicate the stock index, the existing evidence of calendar anomalies can help investors as the clue for the timing of investment.展开更多
文摘This paper aims to examine the existence of calendar anomalies including month-of-year effect, turn-of-month effect, and weekend effect in Thai stock market. The stock return is computed from SET index during 1988 to 2009 and the SET50 index gathered since it was created in 1995. The unit root test is performed to ensure that the stock return series have no unit root. The multiple regression techniques using dummy variables are employed to test the difference of the return during each calendar anomalies period. If the regression model suffers from conditional heteroskedasticity, the GARCH （1, 1） model will be used instead of normal ordinary least square regression. It was found that the calendar anomalies exist in Thai stock market. The return is abnormally high during December and January, which can be addressed to be the turn-of-year effect. The return during the turn-of-month period, which can be defined as the last trading day and the first four trading days of the following months, is also abnormally high. Finally, the return is also abnormally high on Fridays but abnormally low on Mondays, which is addressed as weekend effect. This may create the opportunity to make above-average profit to investors exploiting these calendar anomalies. Although these calendar anomalies may be difficult to be exploited in practice because of transaction costs and ability to replicate the stock index, the existing evidence of calendar anomalies can help investors as the clue for the timing of investment.
