[citation needed] Analysis by Bouman and Jacobsen (2002) shows that the effect has indeed occurred in 36 out of 37 countries examined, and since the 17th century (1694) in the United Kingdom.
[6] Data show that stock market returns in many countries during the May–October period are systematically negative or lower than the short-term interest rate[citation needed].
This appears to invalidate the efficient-market hypothesis (EMH), which predicts that any such returns (e.g., from shorting the market) would be bid away by those who accept the phenomenon.
Alternative causes include small sample size or time variation in expected stock market returns.
[8] A follow-up study by Andrade, Chhaochharia and Fuerst (2012) found that the seasonal pattern persisted.