Testing the day-of-the-week effect and January effect anomalies at Istanbul Stock Exchange with Arch-Garch models

This study investigates the presence of calendar anomalies, particularly January and day-of- the-week anomalies on the daily returns at Istanbul Stock Exchange (ISE). Although there is a vast number of studies on these anomalies which are contrary to the Efficient Market Hypothesis as one of the main theories in finance literature, very few studies covering the whole operation period of ISE from 1987 until today and utilizing GARCH models to test for the anomalous stock market behavior, have been the starting point of this reseach. The research spans the whole period of July 3rd 1987-July 18th 2008 and uses 5157 daily data; and the empirical study applies GARCH (1,1) model, with one lag return series in the mean equation of ISE-100 Index. The results prove that the daily returns of ISE-100 in January do not show a statistically significant difference from other months. For the day-of-the-week anomalies, statistics indicate that ISE-100 daily returns on Fridays are higher than the average as compared to other days, while returns on Mondays are lower.