By Salil Mehta, statistician and blogger at (Statistical Ideas)NEW YORK ( TheStreet) -- The fall months may be some of theriskiest months in the market. After all, most of the infamous 10, worst one-day market panics on the Dow, have occurred near October. But a ranked listing of only10 is a freakishly small sample of extreme events from which to draw any statisticalsignificance. The history of the Dow goes back to the late 19th century. And with enough data, wecan better understand the frequency of when severe market drops occur. We knowthat Mark Twain once said at about the same time the Dow started, "It is notworth while to try to keep history from repeating itself, for man's character willalways make the preventing of the repetitions impossible." There is a statistically strong historicalrepetition of market crashes, occurring in the months near October. But so too docrashes more often occur on Mondays, for any month of the year. Of the 29,400trading days in the history of the Dow, we looked at the worst 294 (or 1%) of them.In order to qualify for this club of the worst 1% days, a daily price drop of at least3.2% was needed. And while we expect five of these worst 1% days biennially, themost recent one we have had was November 2011. Here is the distribution of those 294 days by month, in red on the chart. As astatistical alternate, we also show, in light green, the distribution of 294 days evenlyspread across 12 months.
Next we show the distribution of these worst 1% trading days, by the weekdaywhen they occurred. The statistical strength of Mondays is very powerful, and itdoes not transfer over to either the trading day before or after (e.g., Fridays orTuesdays). We can see this with a simple kernalized smoothing technique, with awidth of plus or minus one day. We see the kernalized distribution essentiallymatches the uniform distribution in light green, so we fail to appreciate that theMonday result is a product of luck during the five-weekday cycle.