Siegel Fires Back on Long-Term Data

Last month, we highlighted Wall Street Journal columnist Jason Zweig’s criticism of the long-term stock return data that Jeremy Siegel has used in his book, Stocks for the Long Run.

Zweig said that the data Siegel used for 1802-1870 was “rotten with methodological flaws”, saying it was cherry-picked, filled with survivorship bias, and included an estimated dividend yield that was likely too high. The criticism was big news — Siegel’s book is something of a bible to buy-and-hold investors because it concludes that stocks have far and away been the best investment vehicle for more than two centuries.

In a recent letter to the editor at the Journal, however, Siegel stood by his data — and says new data backs it up.

“Bill Goetzmann and Roger Ibbotson’s (G-I) recently published article, ‘A New Historical Database for the NYSE 1815 to 1925: Performance and Predictability’ is the most thoroughly documented research on early U.S. stock returns, collecting monthly price and dividend data on more than 600 individual securities over more than a century of data,” Siegel writes, “and it is free from the survivorship bias and other problems which [Zweig’s] article alleged plague the early data.”

Siegel says dividend yield is the biggest source of uncertainty in early stock return data, but Goetzmann and Ibbotson’s data addresses that carefully. “G-I formed two series of dividend yields, one assuming that those stocks for which they could not find dividends had zero dividends (3.77%), and another which uses the dividend yield of those stocks for which they could find dividends (9.27%),” Siegel says, adding that Goetzmann and Ibbotson conclude that the real dividend yield must have been between those two figures. “My dividend yield, which [Zweig’s] article claims is unrealistically high, is 6.4%, actually less than the midpoint of their two estimates,” Siegel says.

Siegel says that in some ways, the debate over early stock return data is overblown. “The case for stocks … relies on the more than 100 past years of data that have been collected not only in the U.S. but in 15 other major world stock markets,” he writes. “And the recent bear market does not invalidate the fact that it has been 150 years since we last had a 30-year period when bonds beat stocks.”

Send a Comment

Your email address will not be published. Required fields are marked *