Month-of-the-year and pre-holiday seasonality in African stock markets

Seasonal anomalies (calendar effects) may be loosely referred to as the tendency forfinancial asset returns to display systematic patterns at certain times of the day, week,month or year. Two popular calendar effects are investigated for African stock returns:the month-of-the-year and the pre-holiday effects, and their implication for stockmarket efficiency. We extend the traditional approach of modelling anomalies usingOLS regressions and, examine both the mean and conditional variance. We find highand significant returns in days preceding a public holiday for South Africa, but thisfinding is not applicable to the other stock markets in our sample. Our results alsoindicate that the month-of-the-year effect is prevalent in African stock returns.However, due to liquidity and round trip transactions cost the anomalies uncoveredmay not necessarily violate the no-arbitrage condition. Finally we discuss promisingareas for future research using developing stock markets data.