Tuesday, September 07, 2004

I think it's notable that there is a negative correlation between the performance in the S&P the day after Labor Day and its performance the rest of the week.  Since 1950, there is evidence that the larger the gain the day after the holiday, the weaker the return for the balance of the week.  When we restrict our look to only those times the S&P made a major move the day after the holiday (say a gain or loss of 1% or more), then the correlation becomes quite large at -0.41.  Even though that correlation is high, due to the small sample size it is not necessarily statistically significant (meaning it could happen by chance alone). Still, I think it's an interesting enough stat to mention in light of today's gains so far.  From the looks of history, a good day after Labor Day was a poor barometer of gains for the rest of the week. 1:27:25 PM