Abstract
Both the day of the week and the month of the year effects are examined for the Ghana Stock Exchange. The latter is an interesting case because (a) it operates for only 3 days per week during the sample period and (b) the increased focus that African stock markets have received lately from both academics and practitioners. Non-linear models from the generalised autoregressive conditional heteroscedasticity (GARCH) family are used in a rolling framework to investigate the role of asymmetries and assess the effects of policy and institutional changes. Contrary to a January return pattern in most markets, an April effect is found for Ghana. The latter disappears in a rolling framework. The day of the week effect is modelled with an asymmetric GARCH model as the benchmark linear paradigm was rejected. Friday's return was found to be the most significant but this seasonality disappears when a rolling window is employed (time-varying asymmetric GARCH).
Keywords
Get full access to this article
View all access options for this article.
