Move over, January: At least two other months have greater predictive power of stock market returns than you.
January has a reputation for predicting the direction of the US market over the next 11 months of a year. This alleged skill is known as the ‘January Forecaster’ and ‘January Barometer’.
You will see many references to this indicator in the coming days as January is officially in the record books as a ‘down’ month – with the S&P 500 SPX,
slipping 1.1%. I have previously written that the January forecaster relies on a shaky statistical basis. Nonetheless, financial headlines will trumpet the alleged negative consequences of the January drop for the remainder of 2021.
So let me list a few other ways the Predictor is not worth following.
What’s so special about January?
A good place to start is to recall that January 2020 was also a downward month (down 0.2%) and the subsequent 11 months delivered an above-average profit of 18.4% nonetheless (assuming dividends reinvested ).
That’s just one data point. Another indication that there is nothing special about January is that other months have even greater predictive “powers” in forecasting the stock market price in the next 11 months. In fact, since the founding of the S&P 500 in 1954, June has the best forecasting power, followed by February. January is in third place.
Then why not read about a June forecast or a February barometer? My suspicion is that followers are motivated less by statistical rigor than by stories and stories that grab their attention. From a behavioral perspective, the calendar year is a more natural period to focus on than the February to February or June to June periods. But psychological significance is different from statistical significance.
The importance of real-time testing
There’s another telltale sign that the January indicator isn’t all it is: It fails real-time tests.
By this I mean tests performed after it was initially ‘discovered’. If the January forecaster could have passed these tests, we would have much more confidence that this is not just the result of a data mining exercise that tortures the historical data long enough for a pattern to emerge.
But it didn’t work out. As far as I know, the real-time test of the January Predictor begins in 1973. According to an academic study on the subject, that is the earliest mention on Wall Street. Unfortunately, his record has been much less impressive since then. In fact, since 1973, not only is it not significant at the 95% confidence level that statisticians often use to determine if a pattern is real, it is not even significant at the 85% level.
We shouldn’t be surprised; actually the January Predictor is in good company. Consider a study published in the Review of Financial Studies last May. It examined 452 supposed statistical patterns (or “anomalies”) that had previously been identified by academic research. The authors of this recent study were unable to replicate these results in 82% of the cases. The remaining 18% turned out to be much weaker than originally reported.
No correlation between the magnitude of January’s increase and returns over the next 11 months
Yet another indication that the January Predictor rests on a shaky statistical basis is that there is no correlation between the strength of the market in January and gains in the following 11 months. If such a correlation existed, we might be able to come up with a plausible story about investor confidence at the beginning of the year, which carries over into the rest of the year.
But there is no such connection. Because of that absence, to believe in the effectiveness of the January Predictor, you would have to believe that an S&P 500 gain of only 0.01 has as much predictive power as a gain of 13.2%. That puts pressure on credulity.
Incidentally, I chose this 13.2% in my illustration because it’s the largest January gain for the S&P 500 since its inception in the mid-1950s. That came in 1987. From January 31 of that year to the end of 1987, the S&P 500 lost 9.9%.
To take advantage of a statistical pattern, you must follow it religiously for years
Finally, even if the January predictor rested on a solid statistical basis, you would have to act on it for years on end to try to profit from it rationally. A good rule of thumb in statistics is that you need a sample size of at least 30 for patterns to become meaningful. In the case of the January forecaster, that means you should be tracking these three decades. In addition, during those 30 years, you would not undertake any trades other than switching to a 100% stock allocation on January 31, when the stock market rises in January, and to a 0% allocation if the market falls in January.
Without that patience and that discipline, you do little to improve your odds over a coin flip.
It comes down to? In all respects, you cannot infer from the stock market’s fall in January as to where it will be on December 31st.
Mark Hulbert is a regular contributor to MarketWatch. His Hulbert Ratings tracks investment newsletters that pay a flat fee to be checked. He can be reached at [email protected]
Lake: Prepare for a 10% stock drop driven by the 3 ‘R’s,’ Bank of America warns
Also read: This surprising stock market timing strategy has academic hallmark