Archive for April, 2010
Today I received the very good news that our proposal with Jean-Michel Marin to undertake “research in pair” in CIRM, Luminy, a fortnight next summer was accepted! This research centre in Mathematics is a southern and French version of the renowned German centre of Oberwolfach and, while I would have prefered the cool Black Forest to the burning rocks of the nearby calanques, I am very grateful for this support from the sponsors of the CIRM centre. We aim at revising the book Bayesian Core towards a Use R! version during this fortnight (if the heat does not kill our legendary productivity!). The CIRM centre is located in a nicely renovated bastide within a small park, and the famous climbing cliffs of the calanques are within walking distance. (I just need to find a climbing partner!) I have organised several meetings there along the years and the atmosphere there is always propitious for research. (There is also a well-provided library, if not comparable to Oberwolfach.)
“Tout étant fait pour une fin, tout est nécessairement pour la meilleure fin. Remarquez bien que les nez ont été faits pour porter des lunettes, aussi avons-nous des lunettes.” Voltaire, Candide, Chapitre 1.
I am now done with my review of Sober’s Evidence and Evolution: The Logic Behind the Science, Posting about each chapter along the way helped me a lot to write down the review over the past few days. Its conclusion is that
Evidence and Evolution is very well-written, with hardly any typo (the unbiasedness property of AIC is stated at the bottom of page 101 with the expectation symbol E on the wrong side of the equation, Figure 3.8c is used instead of Figure 3.7c on page 204, Figure 4.7 is used instead of Figure 4.8 on page 293, Simon Tavaré’s name is always spelled Taveré, vaules rather than values is repeated four times on page 339). The style is sometimes too light and often too verbose, with an abundance of analogies that I regard as sidetracking, but this makes for an easier reading (except for the sentence “the key to answering the second question is that the observation that X = 1 and Y = 1 produces stronger evidence favoring CA over SA the lower the probability is that the ancestors postulated by the two hypotheses were in state 1”, on page 314, that still eludes me!). As detailed in this review, I have points of contentions with the philosophical views about testing in Evidence and Evolution as well as about the methods exposed therein, but this does not detract from the appeal of reading the book. (The lack of completely worked out statistical hypotheses in realistic settings remains the major issue in my criticism of the book.) While the criticisms of the Bayesian paradigm are often shallow (like the one on page 97 ridiculing Bayesians drawing inference based on a single observation), there is nothing fundamentally wrong with the statistical foundations of the book. I therefore repeat my earlier recommendation in favour of Evidence and Evolution, Chapters 1 and (paradoxically) 5 being the easier entries. Obviously, readers familiar with Sober’s earlier papers and books will most likely find a huge overlap with those but others will gather Sober’s viewpoints on the notion of testing hypotheses in a (mostly) unified perspective.
And, as illustrated by the above quote, I found the sentence from Voltaire’s Candide I wanted to include. Of course, this 12 page review may be overly long for the journal it was intended for, Human Genetics, in which case I will have to find another outlet for the current arXived version. But I enjoyed reading this book with a pencil and gathered enough remarks along the way to fill those twelve pages.
When writing the review of Sober’s Evidence and Evolution: The Logic Behind the Science, I incidentaly found that all IMS Lecture Notes books are available on-line, free, through Project euclid. This is fantastic! This is for instance the case for Berger and Wolpert’s classic, The Likelihood Principle.
My brother-in-law Christophe has a mowing robot (called Mara!) that is completely autonomous. It starts from its plug and goes along straight lines until it hits an obstacle or the boundaries defined by an underground cable. Then it turns at random and starts again. The concept is quite interesting but I am surprised that it operates on a purely local random walk principle, without any learning about the topology of the terrain. This means that zones with more obstacles are visited less often. (To compensate for that, the mower starts moving in circles each time it hits denser regions of grass.) And that the mower spends a lot of time looking for its plug. An algorithmic determination of the terrain would be possible, obviously, using for instance a Metropolis-Hastings scheme.
A series of new posting on arXiv I would like to discuss further:
- arXiv:1004.2840 : Robust Parameter Selection for Parallel Tempering by Hamze, Dickson and Karimi
- arXiv:1004.2910 : Valid p-Values using Importance Sampling by Harris
- arXiv:1004.3476 : Approximate Methods for State-Space Modelsby Koyama, Castellanos, Shalizi and Kass
- arXiv:1004.3616 : Recursive Numerical Evaluation of the Cumulative Bivariate Normal Distribution by Meyer
- arXiv:1004.3830 : Model Selection and Adaptive Markov chain Monte Carlo for Bayesian Cointegrated VAR model by Peters, Kannan, Lasscock and Mellen
- arXiv:1004.3925 : Classification using distance nearest neighbours by Friel and Pettitt
especially since the paper by Neal Friel and Tony Pettitt builds upon our JASA k-nearest neighbour paper.