Out-of-sample Dataset Before the “Sample”: Pervasive Returns of Anomalies Before 1926
Baltussen et al. (2021) constructed a database of U.S. stocks, including dividends and market caps for 1488 major stocks from 1866 to 1926. The sample can be described as the pre-CRSP period, including independent, pre-publication, and “out-of-sample” data that can be a perfect test for the factors utilized today.
So what about the findings? The relationship between market beta and returns is insignificant and flat, but the low-beta stocks have highly significant CAPM alpha. Size premium is also negligible. Important factors appear to be momentum (12–1), dividend yield (which serves as a proxy for the value), and short-term reversal. Other crucial findings are that the factor premiums cannot be explained by macroeconomic risk, and the characteristics can explain 28% of the variation in returns. Lastly, the research shows that there are several pervasive factors with insignificant out-of-sample decay in premiums. Overall, the study is perhaps the best out-of-sample test of factors we can get right now.