Publications by Pat
Selections from the R/Finance conference
The R/Finance conference happened in Chicago at the end of April. If, like me, you weren’t there, you can still benefit from it because slides from many of the talks are now online. Here is a quick synopsis (in chronological order) of some of the talks I found most interesting. Michael Kane Michael Kane and colleagues show an analysis of flas...
3461 sym 2 img
Market arrows
Graphs like Figure 1 are reasonably common. But they are not reasonable. Figure 1: A (log) price series with an explicit guide line. Some have the prices on a logarithmic scale, which is an improvement on the raw prices. The problem with this sort of plot is that two particular data points are taken as special. These two points are essentiall...
1606 sym 6 img
Performance ratios, bootstrapping and infinite variances
If returns had infinite variance, would there be a problem bootstrapping information ratios? Background There is a discussion on the Quant Finance group of LinkedIn with the title: “How do you measure the confidence intervals of performance ratios?” One suggestion was to use the statistical bootstrap. This resulted in a discussion of the effi...
4216 sym 18 img
Talking The R Journal latest release
Volume 3/1 of The R Journal has been released. It of course has articles about using R. In addition it has a feature that I highly support. In preparation for the UseR! Conference 2011 August 16-18 in Coventry there are two Help Desk articles on making a good technical presentation. Technical presentation Rob Hyndman writes “Giving a UseR! ...
2249 sym 2 img
Winsorization
Winsorization replaces extreme data values with less extreme values. But why Extreme values sometimes have a big effect on statistical operations. That effect is not necessarily a good effect. One approach to the problem is to change the statistical operation — this is the field of robust statistics. An alternative solution is to just chang...
2972 sym 10 img
Testing an S&P 500 prediction
If a particular prediction comes true, how surprised should we be? The prediction The page that sparked my curiosity tells of a prediction made a year ago that the S&P 500 would beat its historic high by the end of 2011. It says that at the point the prediction was made, the level of the index was about 1010. According to Wikipedia the all-time...
5025 sym 6 img
On “Stock correlation has been rising”
Ticker Sense posted about the mean correlation of the S&P 500. The plot there — similar to Figure 1 — shows that correlation has been on the rise after a low in February. Figure 1: Mean 50-day rolling correlation of S&P 500 constituents to the index. For me, this post raised a whole lot more questions than answers. Which correlation? When I t...
4284 sym 16 img
Registration closing for UseR! 2011
Friday July 22 is the last day on which you can register for UseR! 2011 at the University of Warwick. The conference will be 2011 August 16-18. You can peruse the book of abstracts and view the draft schedule. I am scheduled to give a talk on “Random input testing with R”. The abstract is: Traditional software testing uses specific inputs...
1586 sym 2 img
More S&P 500 correlation
Here are some additions to the previous post on S&P 500 correlation. Correlation distribution Before we only looked at mean correlations. However, it is possible to see more of the distribution than just the mean. Figures 1 and 2 show several quantiles: 10%, 25%, 50%, 75%, 90%. Figure 1: Quantiles of 50-day rolling correlation of S&P 500 cons...
2593 sym 10 img
The indices understate the carnage
The first 6 trading days of August have been bad for the major indices, but how variable is that across portfolios? To answer that, two sets of random portfolios were generated from the constituents of the S&P 500. The trading days are 2011 August 1 — 5 and 8. The returns of the indices for this period were: S&P 500: -13.4% Dow Jones Industr...
2673 sym 8 img