Stock market efficiency in South Eastern Europe: testing return predictability and presence of calendar effects

This paper examines the calendar effects in ten South Eastern European (SEE) stock markets daily returns during the period 2007 - 2014. We focus on three calendar effects: the day of the week effect, the half month effect and the turn of the month effect. Specifically, we analyze existence of each calendar effect separately in the mean and in the volatility of the index returns. We apply standard regression models with dummy variables for the effects in the mean returns, while we apply GARCH(1,1) models with dummy variables for the effects in the volatility of returns. The results present evidence that the day of the week effects in both mean and volatility are present in nine out of ten SEE stock markets. Contrary, the half month effect in mean returns is present only in one SEE stock market, while half month effect in volatility is present in five out of ten SEE stock markets. The turn of the month effect in mean returns is present in six out of ten SEE stock markets. The turn of the month effect in volatility is present in all SEE stock markets.