Publications by Pat
Statistical construction error
Yes, the title is meant to have two readings. The effect The Numbers Guy, among other examples, talks about the UK Office for National Statistics needing to revise its estimate for the construction sector output because of an error. Original: 2.3% growth Corrected: 0.5% growth Here is the Telegraph article cited by The Numbers Guy. The cause The ...
1113 sym 2 img
A view of useR!2011
Start Brian Ripley The conference was opened with a talk by Brian Ripley. I’ll distort his talk into 3 points that came across to me. 1. R Core is finite The time available from R Core members is a strictly limited good. The more that is pushed onto R Core, the less attention to details. That doesn’t sound good. The more things that c...
4457 sym 2 img
Random input software testing
The usual approach to testing software is to create a specific problem and see if the software gets the correct answer. Although this is very useful, there are problems with it: It is labor-intensive It almost totally neglects to test the code that throws errors There can be unconscious bias in the test cases created One alternative is to cre...
1579 sym 2 img
Things I learned at useR!2011
The title says “things” but conferences are mainly about people. Some of it can be serendipitous. For example, one day I sat next to Jonathan Rougier at lunch because I had a question for him about climate models. When Jonathan left, I started a conversation with the person on my other side. That was most certainly intellectually stimul...
3724 sym 6 img
The effect of beta equal 1
Investment Performance Guy had a post about beta equal 1. It made me wonder about the properties of portfolios with beta equal 1. When I looked, I got a bigger answer than I expected. Data I have some S&P 500 data lying about from the post ‘On “Stock correlation has been rising”‘. So laziness dictated that I use that. It is daily da...
4675 sym 18 img
Realized beta and beta equal 1
What does beta look like in the out-of-sample period for the portfolios generated to have beta equal to 1? In the comments Ian Priest wonders if the results in “The effect of beta equal 1″ are due to a shift in beta from the estimation period to the out-of-sample period. (The current post will make more sense if you read that one first.) Re...
2853 sym 12 img
Review of “Risk and Meaning” by Nicolas Bouleau
The subtitle is: Adversaries in Art, Science and Philosophy. Executive Summary Genius or madness? I haven’t decided. Irreversibility of interpretation The book drives home that once we decide how something is we can’t go back to our state of innocence. Figures 1 through 3 exhibit this idea via a randomly generated polygon. Look at Figure 1 ...
5706 sym 14 img
A brief history of S&P 500 beta
Data The data are daily returns starting at the beginning of 2007. There are 477 stocks for which there is full and seemingly reliable data. Estimation The betas are all estimated on one year of data. The times that identify the betas mark the point at which the estimate would become available. So the betas identified by “start 2008″ use ...
2699 sym 8 img
Solve your R problems
download ‘The R Inferno’ Epilogue I’m not a lawyer, but here is my understanding of the rules should you want to extract images from this page: Most of the images are from istockphoto.com. You would need to pay for each image that you want to use. It is unlikely that Sandro Botticelli is going to come round claiming his intellectual prop...
1027 sym 2 img
Beta and expected returns
Some pictures to explore the reality of the theory that stocks with higher beta should have higher expected returns. Figure 2 of “The effect of beta equal 1″ shows the return-beta relationship as downward sloping. That’s a sample of size 1. In this post we add six more datapoints. Data The exact same betas of S&P 500 constituents are us...
2576 sym 14 img