In a recent MarketWatch article, columnist Mark Hulbert suggests that those buying into the so-called “Halloween Indicator”—that is, a six-month upside for stocks—may be disappointed.

“That pattern is based on the historical tendency for the stock market to produce the bulk of its gains between Halloween and the following May Day,” notes Hulbert, adding that the tendency “traces almost exclusively to the third years of the U.S. presidential four-year cycle. In the other three years of that cycle,” he argues, “there is no statistically significant difference between the returns in the Halloween-to-May Day period than in the other half of the year.”

Because we’re in the final year of this president’s term, Hulbert asserts, “this seasonal pattern will be of no help to the stock market over the coming six months.”

Hulbert cites the following data– based on the Dow Jones Industrial Average going back to its creation in the late 1800s–from a study by University of California, Berkeley emeritus finance professor Terry Marsh:

Hulbert writes, “Note carefully that the absence of this seasonal pattern over the coming year doesn’t mean the U.S. stock market won’t perform better over the next six months than it has over the past six. But if it does perform better, it won’t be because of the Halloween Indicator.” He suggests that if investors expect increased economic uncertainty in the coming months, “you might want to reduce your equity exposure.”