Day of the week effect and stock market volatility in Ghana and Nairobi stock exchanges

Abstract

We examine Day-of-the-Week Effect anomaly and volatility in returns on Ghana Stock Exchange (GSE) and Nairobi Stock Exchange (NSE) using daily closing price indices from 2005 to 2014. Ordinary Least Square regression with autoregressive term, GARCH (1, 1), TGARCH (1, 1) and EGARCH (1, 1) were used. There is no evidence of day-of-the-week effect in GSE but there exists Friday effect in NSE. Daily returns could be predicted in NSE but cannot be predicted in the GSE using past prices and returns information. The GARCH model suggests a high degree of persistent in the conditional volatility of daily stock returns in NSE. The TGARCH and EARCH models show no evidence of asymmetry in daily returns in NSE. However, there was no evidence of conditional volatility for GSE-CI. The two markets are inefficient and whiles day of the week effects are irrelevant in making investment decisions in GSE it is relevant in NSE. Reduction in trade settlement periods to t + 1 and promoting internet usage will make market information freely available to all investors hence making the markets more efficient.