Factor models are basically just if you tried to decompose returns into some linear regressions and then pretended it was ergodic it because of a “risk-premium”. Risk premiums don’t necessarily exist but with a lot of these there does exist increasing tail risk with…
better performance of said factors. As seen in 2008 the big brown line of momentum is eventually corrected but that is less of a risk premium reason and because of the august risk of multi-strat funds getting blown up in credit and then covering with momentum forcing… 
Momentum the other way. However for other factors like quality and profitability there is little to no basis for it being a risk factor and the issue with assuming this level of ergodicity is that you may hold a position that no longer has alpha expecting to be compensated…
Of course these linear factors do have a history of laying dormant for a decade or more but these are the most famous 5 factors and hundreds have been identified in the literature with many of them decaying. It is important to note however that a linear combination…
Of factors is not a new factor. For example, many believe low volatility is a factor when it is simply a linear combination of profitability and conservative investment factors. On the long term a lot of modelling revolves around linear models and regressions, where…
Most of your features will be related to quality and a few value with the remaining being beta/momentum exposures. Quality decomposes into many areas form intangibles to pure profitability, all with different behaviours. A key point with this is that factors don’t make…
sense as a returns model because they are, like the rest of the market, non-ergodic, and will not always reward you especially for smaller factors you may be focusing on to try to gain excess returns. Because of reflexive effects of everyone treating factors like…
risk premiums etc even if there is not guaranteed outperformance of the factors they are still a good generalisation of the market returns. That’s why using the largest factors I a great way to do regime shift modelling. That alongside correlation risk premium…
volatility risk premium, and skew/correlation. VIX-VOLI is also great. There are more liquidity and option metrics I won’t go into for now.
End.
End.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
