EMPIRICAL EVIDENCE FOR DAY OF THE WEEK EFFECT IN AN EMERGING MARKET: THE TURKISH CASE

OpenAlex İngilizce

There are many studies which have demonstrated the presence of day of the week effect-a well-known market anomaly-for security returns. Moreover, there are some studies which conclude in favor of day of the week effect in exchange rates. However, one rarely finds any studies which examine the validity of day of the week effect for consumer confidence indices. To the best of our knowledge, there is no study on this topic for an emerging market. This is probably one of the first attempts to assess the day of the week effect on both mean and volatility for daily changes in consumer confidence index in Turkey using the CNBC-e consumer confidence index data during the period of January 2003-July 2008. Employing ordinary least squares method, there is no favorable evidence for the presence of day of the week effect. When we allow variance of errors to be time dependent and model conditional variance using exponential generalized autoregressive conditional heteroskedasticity (E-GARCH) method, we are able to validate day of the week effect both in mean and volatility of the daily changes in consumer confidence index. In our findings, the mean equation exhibits only Friday effect and the lowest volatility is also observed for Friday. Finally, we use nonparametric stochastic dominance (SD) approach by employing several SD tests and we verify the existence of Friday effects.