Stats Long run returns Factor replication

64% of 447 published stock anomalies failed a retest

Trading frictions
93.1%
Intangibles
74.8%
Profitability
58.2%
Value vs growth
54.4%
Momentum
35.1%
Investment
28.9%

Trading friction anomalies fail almost entirely. Momentum has the best record and still fails a third of the time. Source: Hou, Xue and Zhang, NBER working paper 23394.

Academic finance publishes hundreds of factors claimed to predict which stocks rise. When 447 of them were retested with market value weighting, roughly two in three were insignificant. A published edge, on its own, is not evidence that a strategy works.

316Factors published
447Anomalies retested
286, or 64%Failed at t above 2
58%Lost after publication

Members only

The rest of this page is for members

Below this point there are 7 sections, 2 charts and 4 named sources, roughly 900 words of it. Every figure carries the source it came from and the date the data is from.

You can keep browsing every statistic in the library for free. The intro and the summary are always open.