Quantocracy’s Daily Wrap for 01/26/2016

We investigate whether two clustering techniques, k-means clustering and hierarchical clustering, can improve the risk-adjusted return of a random equity portfolio. We find that both techniques yield significantly higher Sharpe ratios compared to random portfolio with hierarchical clustering coming out on top. Our debut blog post Towards a better benchmark: random portfolios resulted in a lot of

We often see statements like linear regression makes the assumption that the data is normally distributed, Data has no or little multicollinearity, or other such blunders (you know who you are..). Lets set the whole thing straight. Linear regression assumes nothing about your data It has to be said. Linear regression does not even assume linearity for that matter, I argue. It is

Recently I posted a number of articles on various breadth diffusion indicators and their relative effectiveness in predicting the health of the S&P 500. The big winner was the system that compared the number of stocks in the historical constituents of the Russell 3000 that were up 30% or more over the last quarter (60 trading days) vs those were 30% or down over the same period. You can read

In the last two articles (here and here), we reviewed the backtest results of 28,840 short options straddles on the Russell 2000 Index (RUT). If you haven't read the last two articles, you may want to first read the introductory article for this series Option Straddle Series – P&L Exits. In this post, I am going to show the P&L results in line-chart form rather than the heat map

I'll leave it to others to chime in whether forward P/E's are useful or not given the fact they typically overstate earnings and I'll ignore that earnings may be at a cyclical peak (more on the latter here). As an aside, technicals in the market are filthy, as most short-term signals I look at are providing caution (example here). BUT, based purely on current forward P/E's