Sell in May and go away must be one of the most famous phrases in the stock market. But is it correct? This is the first time I test this. There is a lot of academic empirical evidence showing this anomaly has been in existence for many decades, both in the USA and elsewhere.
I test the following on SPY from 1993 until today:
- Buy the open in the first day of May, sell the open first day in October, versus
- Buy the open in the first day of October, sell the open first day in May.
My time periods are not equal. I chose exit in October instead of November because I know 4th quarter is the best quarter historically.
Buying the open in May and selling the open in October gives this accumulated chart:
As we can see more or less a flat return over 24 years! There are “just” 9 losing periods, but they average a loss of 10,77% vs. average gain of 7.21% for winning periods.
Buying the open in October and selling the open in May gives this accumulated chart:
Now we are talking. Annual return of 9.04% with 57% exposure in the market (time in the market). Average winning period is 14.04% vs average losing period -11.16%. Just 3 losing periods: 2000, 2007 and 2008 (flat in 1993).