Monthly Archives: November 2010
The good side of inside trading
All About Alpha has a post called Insider traders: rogues or whistleblowers? It is a pleasantly disturbing look at insider trading in that it challenges the reflex reaction that inside trading is all bad. In particular the final paragraph discusses an interesting inconsistency. One issue that is highlighted is that it is harder for negative … Continue reading
Joy of Stats coming soon
The Joy of Stats really is a joy. It will be shown on BBC4, apparently scheduled for December 7. (That date comes from Hans Rosling on twitter, I haven’t found scheduling evidence at the BBC.) I saw its debut at the Royal Statistical Society on World Statistics Day. Here is a five minute excerpt: You … Continue reading
Posted in R language, Statistics
8 Comments
Yet another inferno
Many from the R world will know The R Inferno. Abstract: If you are using R and you think you’re in hell, this is a map for you. A newly minted inferno is The 9 circles of scientific hell. Most amusing to me is Circle 4: p-value fishing, the punishment of which is brilliant. As … Continue reading
Posted in R language, Statistics
Leave a comment
Were stock returns really better in 2007 than 2008?
We know that the S&P 500 was up a little in 2007 and down a lot in 2008. So on the surface the question seems really stupid. But randomness played a part. Let’s have a go at deciding how much of a part. Figure 1: Comparison of 2007 and 2008 for the S&P 500. Statistical … Continue reading
Review of “Obliquity” by John Kay and “Drive” by Daniel Pink
How could a book about indirectly solving problems and one about human motivation be saying the same thing? Obliquity Chapter 1 (and more) is about happiness. We’ve been here before — with a review of The Happiness Equation. Unlike The Happiness Equation, this book gives us some real insight into happiness. Kay divides happiness into … Continue reading
Primitive stock markets
There are two types of technology: Good (does exactly as wanted, with no hassle) Primitive (all the rest) This classification has been instilled into me by my wife. The stock market is primitive. Unbroken history Current stock markets are not much different than when the New York Stock Exchange was the shade of a buttonwood … Continue reading
R is a name you need to know
As if that is news to some of you. Forbes has a Mean Business blog post by Steve McNally titled “Names You Need to Know in 2011: R Data Analysis Software”. The post includes several links to why R is wonderful. It also includes a pretty — but seemingly useless — statistical graph. Correct me … Continue reading
Posted in R language, Statistics
3 Comments
The ARORA guessing game
The game ARORA (A random or real array) is a website that gives you two time series at a time. Your job is to guess which series is real market data and which is permuted data. It’s fun — try it. With some practice you will probably be able to guess which is which well … Continue reading
Posted in Fund management in general, R language
Tagged ARORA, financial Turing test, technical analysis
Leave a comment
Backtesting — almost wordless
On Tuesday I gave a talk at the Thalesians entitled “Effective backtesting”. You can get the annotated slides but below is an almost wordless introduction to backtesting. Introduction Figure 1. When you backtest, you attempt to see how an investment strategy would have worked during some historical period of time. We can think of backtesting … Continue reading
Posted in almost wordless, Quant finance, Random portfolios
Tagged backtesting, outperformance
5 Comments
