The January and Monday effect or the lack thereof

Abstract

This paper assesses the existence of calendar anomalies on 167 stocks listed on the Nigerian stock exchange (“NSE”) between the period 2004 and 2014. These stocks, at different times, also constituted part of the all share index within the review period. The approach taken in this paper differs slightly from most papers where the review has been on indices rather than individual stocks. The simple Ordinary Least Squares (“OLS”) estimation technique and the Generalised Autoregressive Conditional Heteroscedasticity (“GARCH”) model were utilized to test for day of the week effects and any other monthly calendar anomaly that has been reported at different times on the Nigerian Stock Exchange.

The evidence from this study indicates that for the Nigerian Stock Exchange All Share Index (“NSE ASI”), and majority of the listed equity instruments, there was no statistically significant day of the week or month of the year effect. There is no evidence of a January effect or any other monthly effects. The constituents of the NSE ASI were employed because as at December 2014, a single stock on the NSE ASI, accounted for over 20% of the index composition. This has been the case since the year 2010.

Keywords: Calendar anomalies, Nigeria, January effect, Day of the week effect, OLS, GARCH.