Testing Day-Of-The-Week Effect Asymmetry In Borsa Istanbul (Bist)

The aim of this study is to investigate a well-known calendar anomaly hypothesis, namely the day-of-the-week effect, in Borsa Istanbul (BIST). According to that hypothesis, in certain days of the week, stock returns show a regular pattern, particularly on Mondays returns are significantly negative and on Fridays returns are significantly positive, even in the stock markets of developed economies. Hence, this regular pattern presents a distinct challenge to the Efficient Market Hypothesis. For this purpose, a non-parametric multiple comparison test (Steel-Dwass Test) is employed on daily returns of BIST-100 Index, which covers one main and two sub-periods namely, (04.01.1998-27.03.2015), (04.01.1998 - 28.12.2001) and (02.01.2002 - 27.03.2015). The results indicate the existence of the day-of-the-week effect for the main period (04.01.1998-27.03.2015) and for the first sub-period (04.01.1998 - 28.12.2001). The contrary finding is valid for the second sub-period (02.01.2002 - 27.03.2015) and indicates a conclusion that the BIST is free from the day-of-the-week effect. This result could be attributed to the economic stabilization policies pursued in the Turkish economy aftermath of 2001 crisis.