The Supraview of Return Predictive Signals

Here’s the abstract of a recent academic paper:

This study speaks to investment academics and practitioners by describing the population of return predictive signals (RPS) discovered and publicly identified during the period 1970-2010. Our supraview brings to light a number of new facts about RPS, including that many more RPS exist than is commonly realized (our database contains over 330 signals); the statistical properties of newly discovered RPS have remained stable over time; the returns and Sharpe ratios earned by famous RPS such as accruals and momentum are lower than those of the median RPS; and that RPS with higher mean returns also have higher Sharpe ratios. We propose that the investment performance available to practitioners from exploiting the population of RPS may be very large since empirically we estimate that the average cross-correlation between RPS returns is close to zero. We further show that because the average absolute cross-correlation between RPS returns is also low, the probability that an RPS with a significantly positive raw hedge return will have a reliably positive alpha after being orthogonalized against the market, HML, SMB, MOM and five (15) other randomly chosen RPS is 65% (43%). We interpret these results as being good news for academics and practitioners because they suggest that practitioners can expect to create value for their clients by hunting down new sources of alpha, and academics seeking to document a truly new RPS need not orthogonalize the returns of their new RPS against all pre-existing RPS. However, we note that the low average signed and absolute cross-correlations between RPS returns do present a challenge to academics because they imply that either U.S. stock markets are pervasively inefficient, or there exist a very large number of rationally priced sources of risk in equity returns for theorists to understand and explain.

(Via: CXO Advisory)

Posted by on June 4th, 2012 at 9:00 am


The information in this blog post represents my own opinions and does not contain a recommendation for any particular security or investment. I or my affiliates may hold positions or other interests in securities mentioned in the Blog, please see my Disclaimer page for my full disclaimer.