## Archive for October, 2010

## Another ABC rebuttal

Posted in Statistics, University life with tags ABC, Alan Templeton, Bayes factor, Bayesian model choice, BIC on October 31, 2010 by xi'an

“Given that some logical overlap is common when dealing with complex models, this means that much of the literature using ABC is invalid.”Alan Templeton, July 2010.

**I** had not noticed another reply to Templeton’s PNAS diatribe against ABC that was published by Csilléry, Blum, Gaggiotti and François in ** Trends in Ecology and Evolution**. This reply follows a letter written by Templeton to this journal and published last July. Alan Templeton takes issue with the inclusion of a box in the nice survey of Csilléry et al. entitled

*Controversy surrounding ABC*. The letter reproduces earlier arguments I already discussed, in particular the “logical impossibility” to have larger models enjoying smaller posterior probabilities than smaller models [that are special cases]. The conclusion that

“1) ABC can and does produce results that are mathematically impossible; 2) the ‘posterior probabilities’ of ABC cannot possibly be true probability measures; and 3) ABC is statistically incoherent (incoherent methods can violate the constraints of formal logic)”Alan Templeton, July 2010.

is thus bringing no novelty to the debate. It is nonetheless mildly irritating to see that Alan Templeton is still advancing “mathematical errors” as his main argument, despite detailed rebuttals published by mathematicians and mathematical statisticians. As demonstrated by the repeated argument that BIC should replace ABC (!), or the decomposition of in the PNAS reply, he is out of his depth on mathematical grounds. However, that he manages to publish a paper like the PNAS diatribe without the journal having a mathematician checking the “mathematical flaws” is more of an issue.

## A very poor read

Posted in Books with tags book review, steampunk, Worldshaker on October 30, 2010 by xi'an

**F**ollowing some reading advice on tor.com, I ordered ** Worldshaker** by Richard Harland. Now I have read it, I cannot fathom why anyone would see anything positive about the book and even less how it could be nominated for an award! The style is appalling (the same applies to the above trailer and to the cover). The characters are incredibly shallow. The story is completely predictable, to the point there is no suspense whatsoever. (E.g., it is just so clear from the beginning that the two main characters will end up in a romantic relationship. The reason why they do is highly unrealistic, even in a fantasy universe.) The closed universe of the massive moving city (or

*juggernaut*) is inspired from submarines but the description lacks conviction and it is unrealistic to an unbelievable level (like, how does the structure produce wealth to pay for raw materials from populations outside the ship? Why is the size of the working class population much lower than the size of the upper class population, contradicting economic requirements? What is the role of the “filthies” in the production and locomotion processes if they cannot be compelled to work for the upper class? &tc.) The fact that

**apparently belongs to the “young adult literature” category does not excuse those low standards in writing, unless the author wants to reach at such a young age that the story becomes inappropriate… There is no possible comparison with other books in the literature: the closed universe of a Jules Verne’s novel like**

*Worldshaker***is way above in its creativity, not to mention its style. The hardship of Victorian education are described in Dickens’**

*20,000 leagues under the sea***, that**

*Oliver Twist***very poorly imitates in this respect. The consequences of storing one’s ancestor bodies in one’s lodging is exploited in Barjavel’s**

*Worldshaker**. And so on. (An hilarious confusion on amazon author’s page mixes the author with a homonymous literary theorist!) This is clearly one of the worst novels I have read in a long time…*

**Ravage**## Riemann, Langevin, Hamilton, &tc

Posted in Statistics, University life with tags Hamiltonian Monte Carlo, Read paper on October 29, 2010 by xi'an**T**oday was the deadline for sending discussions on the Read Paper by Girolami and Calderhead. Along with Magali Beffy (who is doing a PhD with Nicolas Chopin and myself) and Jean-Michel Marin, we submitted three discussions, running along the arguments made in this earlier post. They are available as

- Marin and Robert’s discussion,
- Beffy and Robert’s discussion,
- Robert’s discussion.

## Random generators for parallel processing

Posted in R, Statistics with tags Mersenne twister, Monte Carlo methods, parallel processing, random number generation, SPRNG on October 28, 2010 by xi'an**G**iven the growing interest in parallel processing through GPUs or multiple processors, there is a clear need for a proper use of (uniform) random number generators in this environment. We were discussing the issue yesterday with Jean-Michel Marin and briefly looked at a few solutions: Continue reading