A look at the distortion from predicted to realized. The idea The efficient frontier is a mainstay of academic quant.  I’ve made fun of it before.  This post explores the efficient frontier in a slightly less snarky fashion. Data The universe is 474 stocks in the S&P 500.  The predictions are made using data from 2010.  The realized period is 2011. The return predictor is MACD — essentially a momentum estimate.  As before this is used neither to praise nor to denigrate it, but...

The Portfolio Probe blog is caught by two blog aggregators. Finance MoneyScience has an aggregation of financial blogs.  It now catches 50 blogs. R R Bloggers captures the Portfolio Probe posts that are in the R Language category.  It gets posts from over 300 blogs that talk about R. Figure 1 shows a plot of the increase in the number of R bloggers over time.  This is from Graph of the Week in the post “R-Bloggers Steadily Growing”.  I’m biased of course, but I think this plot...

How fat tailed are returns, and how does it change over time? Previously The sister post of this one is “A slice of S&P 500 skewness history”. Orientation The word “kurtosis” is a bit weird.  The original idea was of peakedness — how peaked is the distribution at the center.  That’s what we can see, as in Figure 1.  But it is the tail that wags the model.  The modern idea of kurtosis is of fat tails (or long tails). Figure 1:  Densities of a...

Most popular posts in 2012 As of 2012 January 31. The top 7 portfolio optimization problems A slice of S&P 500 skewness history Review of “Models. Behaving. Badly.” by Emanuel Derman Market predictions for years 2011 and 2012 Physical books of ‘The R Inferno’ and ‘S Poetry’ The distribution of financial returns made simple A tale of two returns (posted in 2010) Solve your R problems (posted in 2011) How to search the R-sig-finance archives The number 1...