Equity investors will likely sweat in August if recent market history repeats itself
August, not April, is the cruelest month, that is, for stock market investors. August has often been the best performing month, convincing investors that a hot August is more than a fluke. But there have been long stretches when the market’s comeback in August has been particularly painful.
Consider the Dow Jones Industrial Average DJIA,
dating back to its inception in 1896. Over the next century, August held the top spot for average performance, with the Dow Jones producing an average gain of 1.8% for the month, more than four times the return average of 0.4% of all other months. .
Yet for the past 35 years, since 1986, August has on average been the worst month for the US stock market – even worse than September, which is well known as a terrible month for stocks. The average Dow Jones return in August since 1986 is minus 0.67%, slightly worse than September’s minus 0.64% – and against an average gain of 1.05% for the other calendar months.
The difference between August’s average return and that of other months is significant at the 95% confidence level that statisticians often use to determine if a trend is genuine. In other words, it was statistically significant when August did significantly better than other months – and when it lagged.
How can two opposites both be statistically significant? To understand the answer, we must realize that statistical significance is a necessary, but not sufficient, condition for concluding that a pattern actually exists. There must also be a plausible theory as to why the pattern should exist in the first place. Still, no plausible theory exists for the month of August, as far as I know.
This discussion already amounts to a cautionary tale about the dangers of data mining. But investors’ appetite for slicing and slicing the data is insatiable. So I can’t ignore other alleged patterns involving August.
One such trend is that August is a particularly lean month in midterm election years, such as this one. Another is that the odds are against August during economic recessions, which may apply to this year, although we won’t know for sure until recession assessors from the National Bureau of Economic Research have not decided – which could take months. Either way, none of these putative patterns are significant by traditional standards of statistical significance.
The bottom line? The behavior of the stock market this month will have nothing to do with August.
Mark Hulbert is a regular MarketWatch contributor. His Hulbert Ratings tracks investment newsletters that pay a fixed fee to be audited. He can be reached at firstname.lastname@example.org
After: Will the stock market rally turn into a clearance sale? This bond market gauge could alert investors
More: JP Morgan quant who called stocks’ summer rebound says rally could continue even as corporate earnings decline