Is there any research done on the interplay between statistical factors (as a result of principle component analysis PCA) and the market factors (especially value, size, low vol, momentum, quality)?
I think that if I can represent a factor by a portfolio then I can look at the exposures of this portfolio to the factor. This is more or less easy for momentum and other ranking constructions. I have to check how to deal with the changing nature of the PCAs. They change through time and so do the market factors. I will see.
The question: who has done analysis on this? Are there posts or papers on the net?