Return Forecasting via (Robust) Regression in quant analytics
High! Can anybody suggest a good reference paper on Return Forecasting via factor regression.
In particular I am interested in the optimal choice of the return frequency (daily, weekly, monthly…) and on the pros and cons of using overlapping returns (say monthly or quartely) returns.
In fact, I am interested in low turnover portfolios.
Another question, does anybody knows any reference on robust regression methods applied to finance and return forecasting?
I’d suggest: Portfolio Selection with Robust Estimation
It applies robust regression methods to compute optimal portfolios. Although nothing to do with return forecasting.
Daily returns understate beta. Monthly is better, if available.
Chapter 6 of the book “Introduction to Modern Portfolio Optimization with NuOPT, S-PLUS and S+Bayes” by Bernd Scherer and Doug Martin talks about robust statistical methods and portfolio construction. Are you looking for something more specific?
NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!