Essays · Method

What has to be true before we publish a factor

Method · Marnello LLC

A factor is a rule for ranking securities. Momentum ranks by trailing return; low volatility ranks by trailing realized volatility. The rule itself is public knowledge. What matters is whether the ranking is built correctly and whether it has done, out of sample and after costs, what the literature says it should.

Marnello applies three tests before a factor is presented as a source of return. A Fama-MacBeth cross-sectional regression has to show a risk premium with a t-statistic above 2. Decile portfolios have to show a positive information ratio in a holdout period that was not used to build the factor. And the top-minus-bottom decile spread has to remain positive after 20 basis points per side of transaction cost. Separately, where a public counterpart exists (momentum and size), the in-house series is compared with the corresponding series from the Kenneth R. French Data Library, so that anyone can check the construction independently.

A factor that fails is still computed and reported, because a portfolio's exposure to it is a fact about that portfolio whether or not the factor earns a premium. It is simply labeled as a risk descriptor rather than a return source. In the current library, 1 of 4 families meets the rule on the free-data universe; the validation record says so.

Essays are general research and commentary. They describe method and practice; they are not legal or compliance advice and not tailored to any firm. Standard disclosure applies.

Sample issues.

Enter your firm email to open the sample issues. The Monthly Quantitative Note follows each month; unsubscribe any time.

Firm addresses only. The address is used to send the Note and to reply to enquiries, and for nothing else. Privacy. Sample issues: Samples.