Stocks always go up in the long run.

The case for the claim starts with a large body of data. The UBS Global Investment Returns Yearbook, built on work by finance professors Elroy Dimson, Paul Marsh and Mike Staunton, finds that US shares returned 6.6 percent a year after inflation from 1900 to 2025, compared with 1.6 percent for bonds¹.¹ It also reports that equities were the best performing asset class in all 21 Yearbook countries with continuous investment histories. See the 2026 public summary (https://www.ubs.com/content/dam/assets/wm/static/cio/documents/giry2026-summary-public.pdf).

Two limits sit inside that sentence. First, “continuous investment histories” leaves out markets that were closed or wiped out, so the countries counted are, in part, those whose markets survived. A sample picked after the fact tends to flatter returns, a point the authors of a separate 16-country study also warn about when they construct their indices.² Second, “best asset class” describes averages over more than a century, not a promise for any 10 or 20 year stretch.

How rough can the ride be? The Yearbook says that, since 1900, equities and bonds have on several occasions lost more than 70 percent in real terms¹.¹ The 16-country study finds that average real returns on shares, measured over decade-long windows, were as high as 16 percent and as low as minus 4 percent a year.² Even a long holding period has contained a decade in which investors lost ground after inflation.

Japan shows the longest wait in a major market. The Nikkei 225 closed at 38,915.87 on 29 December 1989 and did not close above that level until 22 February 2024, when it ended at 39,098.68, 34 years and 2 months later³.³ The Nikkei is an index of share prices, so the figure leaves out dividends received along the way, and it does not adjust for inflation. A buyer who held the whole market and reinvested payouts would have done better than the price index alone suggests, but the point remains: the recovery in price took more than three decades. Details are in this nippon.com data note (https://www.nippon.com/en/japan-data/h01927/).

What is not known: nobody knows whether the next century will repeat the record of the last one, and the countries with the best records were, in part, those that avoided wars, revolutions and closed markets. The data cannot tell a reader how long they will have to wait, or whether a given market belongs with the winners.