In connection with Dawkins’ The God delusion, which review is soon to appear on the ‘Og, a poster at an exhibit on evolution in the Harvard Museum of Natural History, which illustrates one of Dawkins’ points on scientific agosticism. Namely, that refusing to take a stand on the logical and philosophical opposition between science and religion(s) is not a scientific position. The last sentence in the poster is thus worse than unnecessary…
Archive for Cambridge
A new Joint Statistical meeting (JSM), first one since JSM 2011 in Miami Beach. After solving [or not] a few issues on the home front (late arrival, one lost bag, morning run, flat in a purely residential area with no grocery store nearby and hence no milk for tea!), I “trekked” to [and then through] the faraway and sprawling Boston Convention Centre and was there in (plenty of) time for Mathias Drton’s Medalion Lecture on linear structural equations. (The room was small and crowded and I was glad to be there early enough!, although there were no Cerberus [Cerberi?] to prevent additional listeners to sit on the ground, as in Washington D.C. a few years ago.) The award was delivered to Mathias by Nancy Reid from Toronto (and reminded me of my Medallion Lecture in exotic Fairbanks ten years ago). I had alas missed Gareth Roberts’ Blackwell Lecture on Rao-Blackwellisation, as I was still in the plane from Paris, trying to cut on my slides and to spot known Icelandic locations from glancing sideways at the movie The Secret Life of Walter Mitty played on my neighbour’s screen. (Vik?)
Mathias started his wide-ranging lecture by linking linear structural models with graphical models and specific features of covariance matrices. I did not spot a motivation for the introduction of confounding factors, a point that always puzzles me in this literature [as I must have repeatedly mentioned here]. The “reality check” slide made me hopeful but it was mostly about causality [another of or the same among my stumbling blocks]… What I have trouble understanding is how much results from the modelling and how much follows from this “reality check”. A novel notion revealed by the talk was the “trek rule“, expressing the covariance between variables as a product of “treks” (sequence of edges) linking those variables. This is not a new notion, introduced by Wright (1921), but it is a very elegant representation of the matrix inversion of (I-Λ) as a power series. Mathias made it sound quite intuitive even though I would have difficulties rephrasing the principle solely from memory! It made me [vaguely] wonder at computational implications for simulation of posterior distributions on covariance matrices. Although I missed the fundamental motivation for those mathematical representations. The last part of the talk was a series of mostly open questions about the maximum likelihood estimation of covariance matrices, from existence to unimodality to likelihood-ratio tests. And an interesting instance of favouring bootstrap subsampling. As in random forests.
I also attended the ASA Presidential address of Stephen Stigler on the seven pillars of statistical wisdom. In connection with T.E. Lawrence’s 1927 book. (Actually, 1922.) Itself in connection with Proverbs IX:1. Unfortunately wrongly translated as seven pillars rather than seven sages. Here are Stephen’s pillars:
- aggregation, which leads to gain information by throwing away information, aka the sufficiency principle [one may wonder at the extension of this principleto non-exponantial families]
- information accumulating at the √n rate, aka precision of statistical estimates, aka CLT confidence [quoting our friend de Moivre at the core of this discovery]
- likelihood as the right calibration of the amount of information brought by a dataset [including Bayes' essay]
- intercomparison [i.e. scaling procedures from variability within the data, sample variation], eventually leading to the bootstrap
- regression [linked with Darwin's evolution of species, albeit paradoxically] as conditional expectation, hence as a Bayesian tool
- design of experiment [enters Fisher, with his revolutionary vision of changing all factors in Latin square designs]
- residuals [aka goodness of fit but also ABC!]
Maybe missing the positive impact of the arbitrariness of picking or imposing a statistical model upon an observed dataset. Maybe not as it is somewhat covered by #3, #4 and #7. The reliance on the reproducibility of the data could be the ground on which those pillars stand.
During my trips in the recent weeks, I managed to read a few books, although nothing spectacular:
Arnaldur Indriðason’s Outrage (Myrká in Icelandic) is a thriller in the Erlandur series, where inspector Erlundur does not appear at all but is replaced with inspector Elinborg who deals with the murder of a drug rapist. And her family problems. The book got a prize in France and its focus on women issues makes it more interesting than the polce story itself, which meanders quite a lot and relies on too many coincidences. But I do like the stuffing no-exit (huis clos) atmosphere. (The above image is the critique in French from Le Canard Enchaîné.) Given that Erlundur has disappeared, this book stands in between other Indriðason’s books, Hypothermia (Harðskafi) and Black Skies (Svörtuloft).
I had mentioned my uneasiness about Hoffman’s The Left Hand of God a few months ago, both because of a very uneven style, a plot borrowing so much to real events and locations, and a highly ambiguous central character. I nonetheless read the second tome, The Last Four Things, following a request from my son. My impression has definitely not improved, mostly again for a high rate of borrowing from existing facts and places (like Chartres used for the papal seat). The title itself is found in many books and comes from a painting by Bosch I missed in Madrid last time I visited El Prado. The characters are mostly the same ones as in The Left Hand of God and they remain shallow and unconvincing. The political plot(s) are of no interest whatsoever. The reunion between Cale and Arbell is botched, to say the least. (And still some people love it!)
Another thriller I quickly read is Susanna Gregory’s Mystery in the Minster, the 17th chronicle of Matthew Bartholomew… In line with the recent chronicles in the series, the book is not worth any level of recommendation. The plots get thinner and thinner, the dialogues and settings less and less realistic for their 14th Century environment, and the resolution is rushed with no even a pretence of disguise for the massive infodump in the Epilogue! It feels like I have already seen it all in previous books: the trip away from Cambridge to gather an uncertain inheritance, the flow of new characters taking an unreasonable interest in Michelhouse affairs, an endless sequence of deaths, poisons, “wanton” nuns, attractive women turning into insane murderesses, fights for life in an abandoned and crumbling church, &tc. Among the many implausible facts in the current volume, the vicar-chorals’ obsession with shoes, speaking of “intelligent, liberal people” as in a 21st Century society, or hiring an actor to play the role of a (long dead) priest for more than a month… I will for certain abstain from buying the incoming 18th chronicle, appropriately planned for April the 1st!
When ordering books from amazon.fr for my daughter, I added Ascension, a manga by Shin’ichi Sakamoto about climbing. I was however quite disappointed by the result, both for the silly plot and for the lack of realism in its climbing connection!
No, this is not a signal for post-partum depression, even though I really enjoyed my time there!, but the title of a book I got almost for free while in Cambridge Waterstone’s, at the desk as I was paying for The Alloy of Law (also on reduced price, thankfully!) and a Trollope I had not read… Cambridge Blue is a detective story written by Alison Bruce and entirely taking place within Cambridge, which makes for an additional attraction if you are familiar with the place. Overall, this is a pleasant thriller (if I may attach such opposite terms!) with a good if unlikely central character, as well as a whole range of plausible culprits. Maybe the strongest point remains that it takes place in Cambridge after all. (This is the first novel of Alison Bruce. I hope it does not end into a stale series as another Cambridgian series did, namely the initially superb Susana Gregory’s Matthew Bartholomew that have gradually become so disappointing…)
When I saw that The Alloy of Law was half-price in the Cambridge Waterstones, I did not hesitate long in picking the latest Brandon Sanderson‘s book! It is set in the Mistborn universe, with the same chemical principles directing magical powers (allomancy and ferromancy). A terrific concept by the way! However, The Alloy of Law reads much more like a steampunk novel. With a serving of wild (or weird) West. And, in short, it does not read very well… (Even though it reads fast, I was done with it by Sunday evening.)
“Numbers, patterns, movements. People seem erratic, but they actually follow patterns. Find the deviations, isolate the reason why they deviated, and you’ll often learn something. Aluminum on the floor. It’s a deviation.” (p.178)
In a sense, the novel The Alloy of Law best compares with is Gilman’s The Half-made World, that I read about a year ago. Same steampunk basics, same wild wild West atmosphere, same central characters of a female academic chafing at the Victorian constraints imposed by the society, same major role of trains… However, I feel The Half-made World is a successful and convincing construction, while The Alloy of Law sounds like an unfinished attempt. I have been amazed at the number of books published by Sanderson over the past years, especially considering the pressure he is under for completing Jordan’s Wheel of Time series. I wish he had spent more time and care in polishing this book! Indeed, it greatly feels like it was rushed, with a neat idea for a backbone, but not enough meat to make the concept stand. There are too many dreary, repetitive, and overly precise descriptions of gun battles, the main male character is shallow (and only too well deserves his nickname of Wax!), the female character is more interesting but still caricaturesque, the overall plot does not make much sense, most of the dialogues are poor (e.g., when explaining “When you make an alloy, you don’t just mix two metals. You make a new one.“, p. 134), and the connection with the original trilogy is almost completely lost! (The fan-made trailer is actually quite well-made, by comparison. And covering about all main features of the book!)
I am certainly not looking forward the second volume in the series…., if any. In fact, the book is presented as a stand-alone novel, but the ending has all the loose threads (main villain still at large, love relations still unresolved, final appearance of a mythical figure, …) to proceed quickly (too quickly!) to a sequel of The Alloy of Law.