Move over, January: at least two other months have a greater predictive power of returns than you.
January has the reputation of being able to predict the direction of the US market over the next 11 months of a year. This alleged ability is known as the “January Predictor” and “January Barometer”.
You will see many references to this indicator in the coming days, now that January officially appears in the record books as an ‘off’ month – with the S&P 500 SPX
gly 1.1%. I have written before that the January predictor rests on a shaky statistical basis. Financial headlines will nonetheless trumpet the alleged negative effects of the January decline for the rest of 2021.
So let me point out a few other ways in which the predictor is not worth following.
What’s so special about January?
A good place to start is to remember that January 2020 was also a decline (with a 0.2% decrease) and that the following 11 months still yielded an above average return of 18.4% ( if we assume that dividends have been reinvested).
This is just a data point. Another idea that there is nothing special about January is that other months have a greater predictive ‘power’ when they predict the direction of the stock market over the next 11 months. Since the S&P 500 creation in 1954, June has had the strongest forecasting ability, followed by February. January is in third place.
So why not read about a June forecast or a February barometer? My idea is that fans are less motivated by statistical accuracy than by stories and narratives that grab their attention. From a behavioral point of view, the calendar year is a more natural period to focus on than the periods from February to February or June to June. But psychological significance is different from statistical significance.
The importance of real-time testing
There is another sign that the January indicator is not quite right: it does not succeed in time.
By this I mean tests that were performed after it was initially ‘discovered’. If the January forecaster could pass these tests, we would have much greater confidence that it is not merely the result of a data mining process in which the historical data is tortured long enough to reveal a pattern.
But it could not. As far as I can tell, the real-time test of the January Predictor began in 1973. This is the earliest mention of it on Wall Street, according to an academic study on the subject. Unfortunately, the record has been far less impressive since then. Since 1973, in fact, it is not only significant at the 95% confidence level that statisticians often use when determining whether a pattern is genuine, but even at 85%.
We should not be surprised; actually the January forecaster is in good company. Consider a study that appeared in the Review of Financial Studies last May. There were 452 putative statistical patterns (or “deviations”) examined that academic research was found to exist. The authors of this recent study were unable to replicate these results in 82% of cases. The remaining 18% appears to be much weaker than originally reported.
No correlation between the volume and yield of January in the next 11 months
Another clue that the January forecaster is based on a shaky statistical basis is that there is no relationship between the strength of the market in January and the profit in the following 11 months. If there had been such a correlation, we might have been able to convey a plausible story about investor confidence at the beginning of the year for the rest of the year.
But there is no such correlation. Due to the absence, you have to believe that an S&P 500 profit of just 0.01 has as much predictive power as a profit of 13.2% to believe in the efficiency of the January forecaster. It strains credibility.
By the way, I chose this 13.2% in my illustration because it is the biggest January profit for the S&P 500 since its inception in the mid-1950s. It comes in 1987. From 31 January of that year to the end of 1987, the S&P 500 loses 9.9%.
To take advantage of a statistical pattern, you must follow it religiously for years
Ultimately, even if the January forecaster is based on a solid statistical basis, you will have to act on it for years in a row to rationally try to take advantage of it. A good rule of thumb in statistics is that you need an example of at least 30 before patterns become meaningful. In the case of the January forecaster, that means you have to follow it for three decades. Furthermore, you will not undertake any other transactions during the thirty years, except that you allocate a 100% share every 31 January in which the stock market rises, and after a 0% allotment if the market is lower in January.
If you do not have the patience and discipline, do little to improve your chances over a coin.
The conclusion? For all intents and purposes, you can deduce nothing from the decline in the stock market in January about where it will stand on December 31st.
Mark Hulbert makes regular contributions to MarketWatch. His Hulbert Ratings monitors investment newsletters that pay a fixed fee to be audited. He can be reached at [email protected]
More: Get ready for a 10% drop, driven by the 3 ‘Rs,’ warns Bank of America
Also read: This Surprising Stock Market Timing Strategy Has Academic Selection