A promising timing strategy in equity markets

Abstract

In a working paper, Jacobsen and Bouman (2001) claim that that the old stock market saying of ?sell in May and go away but buy back by St. Leger Day? produces statistically significant profit when tested on a large database of equity market returns over the last decade, three decades, and even longer periods. In a recently published paper, Sullivan, Timmerman and White (2001) dismissed the statistical significance of this or any other calendar-based trading rule, attributing the reported test results to a large data mining exercise of the academic and financial communities. In this paper, we provide an out-of-sample test on the Bouman and Jacobsen strategy and conclude that the reported results are indeed statistically significant. In doing so we reintroduce a reliable index of capital returns on the Irish equity market maintained contemporaneously by the Irish Central Statistical Office (and its forerunner) since January 1934 which, in its early decades, displays markedly different statistical properties to both the US and UK equity markets of that time and equity market returns generally in recent decades. As a subsidiary exercise we reconsider the extensive literature on monthly seasonality in equity markets with this novel index. It is contended that the abnormally high returns frequently reported in January and April and occasionally in February and other months are perhaps more accurately and certainly more parsimoniously ascribed to the half-year effect captured in the old stock market adage.