Munger Models: Regression to the Mean
"You must think in a multidisciplinary manner. You must routinely use all the easy-to-learn concepts..." -Charlie Munger
This is the first post in the “Munger Models” series, where I will provide detailed explanations of the 100+ mental models needed to use Charlie Munger’s multidisciplinary approach to thinking.
What Is Regression to the Mean?
Regression to the mean is a statistical tendency that was first popularized by Sir Francis Galton during the late 19th century.
Remember These 3 Things
Regression to the mean describes how extreme data points tend to move closer to the average over time.
The concept reminds us that extraordinary outcomes often follow a return to more typical results.
Recognizing it helps us make more informed predictions and decisions.
How Can We Use This Model?
As investors, regression to the mean reminds us that extraordinary performance—whether good or bad—is often followed by something more ordinary, not because of a change in strategy or effort, but simply due to the statistical inevitability.
One of my favorite financial authors and journalists, Jason Zweig, says:
“From financial history and from my own experience, I long ago concluded that regression to the mean is the most powerful law in financial physics: Periods of above-average performance are inevitably followed by below-average returns…”
Understanding of regression to the mean keeps me from making the costly mistake of extrapolating past trends to excess. This is an easy mistake to make, especially when a trend has gone on for a long time.
Uncovering Charlie Munger’s Wisdom
Charlie Munger said this about stock market returns (and regression toward the mean) at the 1997 Berkshire Hathaway Meeting:
The one thing we can confidently guarantee is that real inflation-adjusted returns from investing in a standard collection of stocks will be lower in the long-term future than they’ve been in the last 15 years or so.
This has been an unprecedented period, and there will be some regression toward the mean in average returns from investing in the stock market.
Thanks to this tool, we can see that Munger’s prediction was right.
1982-1997: The inflation-adjusted return for the S&P 500 is ~739%, or 14% per year.
1998-2013: The inflation adjusted return for the S&P 500 is ~76%, or 3.6% per year.
In the same meeting, Warren Buffett said:
It is worth pointing out that corporate profits, as a percentage of GDP, are right at the all-time high, leaving out a few aberrational periods. And I would — you know, if I had to bet on the direction of corporate profits, as a percentage of GDP, over the next five years, I would bet they would go down somewhat. But that’s because they’re right at this very high level…you might expect something of a reversion to the mean.
🌎 How the World Really Works
In essence, regression to the mean teaches us humility in the face of randomness, caution in interpretation, and the importance of perspective.
It's a reminder of the world's inherent variability and the need for thoughtful analysis in understanding and navigating it.
Limitations of This Model
What are the models? Well, the first rule is that you’ve got to have multiple models. —Charlie Munger
When making decisions or predictions about the future, understanding regression to the mean can help in calibrating expectations.
However, using regression to the mean as a sole decision-making tool can be overly simplistic. It's essential to consider other factors and data when forecasting or making decisions.
Imagine an investor who observes a company at an all-time low. If they over-rely on this model, they may buy the stock, thinking it’s inevitable that the performance will revert to the mean. But the company’s price could reflect the fact that the business fundamentals are garbage.
Remember This: While the future isn't entirely predictable, understanding statistical principles like regression to the mean can help us set more realistic expectations and make better decisions.
