Goldman Sachs destroys one of the most persistent myths about

A version of this post was originally published on TKer.co.

Let’s talk about the CAPE ratio. It’s one of the most widely-followed stock market valuation and investing metrics. It’s being talked about more as investors wonder whether stocks are poised to lose ground in 2022. Unfortunately, the signal of doom it supposedly sends is a myth.

CAPE, or cyclically adjusted price-earnings, was popularized by Nobel prize-winning economist Robert Shiller. It’s calculated by taking the price of the S&P 500 and dividing it by the average of 10 years’ worth of earnings. When CAPE is above its long-term average, the stock market is thought to be expensive.

Many market watchers use above-average CAPE readings as a signal that stocks should underperform or even fall as it reverts back to its long-term mean.

But CAPE’s mean doesn’t actually have much pull.

“While valuations feature importantly in our toolbox to estimate forward equity returns, we should dispel an oft-repeated myth that equity valuations are mean-reverting,” Goldman Sachs analysts wrote in a new note to clients.

The analysts began their discussion by noting that the problematic assumption that a mean exists for metrics like CAPE to revert to.

“Mean reversion assumes that market valuation metrics … are stationary and their long-term means do not change,” they wrote.

In recent decades, valuation metrics have been persistently high, which have actually forced these long-term means to move higher. Not long ago, GMO’s Jeremy Grantham made this observation to argue that valuations were in a “new normal” at elevated levels.

‘We have not found any statistical evidence of mean reversion’

At any rate, the case for mean-reversion is weak.

“We have not found any statistical evidence of mean reversion,” the Goldman Sachs analysts wrote. “Equity valuations are a bounded time series: there is some upper bound since valuations cannot reach infinity, and there is a lower bound since valuations cannot go below zero. However, having upper and lower bounds does not imply valuations are stationary and revert to the same long-term mean.”

Story continues

The Goldman analysts did the math, and the key metric to look at in the chart below is the statistical significance.

“The statistical significance over the full sample is 26%. This means that there is only 26% confidence that the Shiller CAPE is mean-reverting, and 74% confidence that it is not. The traditional threshold to consider a relationship statistically significant is 95%.”

In other words,…