I was reading today’s Guardian and came across Zoe Williams’ sketch (in UK newspapers, this is a short, often humorous, descriptive piece, usually about an event like a parliamentary debate or court proceedings), “Rebekah Brooks lays bare the secret of her success”, recounting the appearance of former News International CEO Rebekah Brooks at the Leveson Inquiry into “phone hacking” and the too-cozy relationship between the media and politicians.

The sketch was mostly remarkable for what it couldn’t say. Williams writes

But ultimately, this is a ridiculous person. You couldn’t live a life with this bad a memory. Never mind that you’d never be able to do a demanding job, you wouldn’t be able to pass your GCSEs.

And that makes the whole business grating to watch. “I can’t remember” is the defence of a person who wasn’t really concentrating, whose mind was somewhere else.

And this makes the whole business grating to read. I don’t think this is only an indulgence in some old-fashioned British circumlocution: Williams really means “I think Rebekah Brooks was lying”. But I assume she can’t write that, because that would be accusing Brooks of the crime of lying under oath, and Brooks would be free to sue for libel — and under UK libel law, the burden of proof is on the defendant to prove the statement true, impossible in this case. (I am not a lawyer, but this is my understanding.)

This is just one of the minor repercussions of the current state of UK libel law, which the government may be overhauling soon — it was discussed in last week’s Queen’s Speech (another amusing tradition in which the Monarch reads a speech written by the government recounting its plans for the next parliamentary session). Simon Singh, a science writer who was sued for liable by the [redacted] of the chiropractic industry, writes that the proposal still doesn’t go far enough, especially in its lack of distinction between individuals and corporations. (Americans may think this sounds familiar from a different context.)

The weakest spot was “The explanation of concepts given by the lecturer” with 5 for satisfactory, 11 for good and 7 for very good — I suppose this reflects the actual difficulty of some of the material. In the second half of the course I need to draw more heavily on concepts from particle physics and thermodynamics that undergraduate students may not have encountered before, concepts that are necessary in order to understand how the Universe evolved from its hot, dense and simple early state to today’s wonderfully complex mix of radiation, gas, galaxies, dark matter and dark energy. Without several days to devote to the nuclear physics of big-bang nucleosynthesis, or the even longer necessary to really explain the quantum field theory in curved space-time that would be necessary to get a quantitative understanding of the density perturbations produced by an early epoch of cosmic inflation, the best I can do is give a taste of these ideas.

And I really appreciated comments such as “Work with other lecturers to show them how it’s done”. So thanks to all of my students — and good luck on the exam in early June.

It has been set up by the excellent lonyla (London-NY-LA) artists’ network founded by J. Dakota Powell, another American transplanted to London, taking advantage of the connections that we rootless cosmopolitans have gathered over years of transatlantic and intercontinental living and travel. How do we tell stories to each other across such vast distances in space and in culture?

TimeWave itself will try to realise these long-distance links. One event, multiple locations, multiple points of view, even within a single piece:

Each day of the festival will consist of a two-hour event, knitting together 8 to 10 short pieces from playwrights, poets, composers and transmedia creators to form a kaleidoscopic tapestry. Over a five-day run, the programme will resemble a prism shifting every few minutes to reveal a unique voice, style or viewpoint.

In some pieces, we will use telepresence. For example, American actors will be live-streamed on to a projection screen to interact with British actors on stage. Or audiences in Hong Kong can discuss what they’ve seen with audiences in Manchester, sharing thoughts and ideas.

The festival has already got the support of an amazing group of writers, filmmakers and directors, including Neil LaBute and David Henry Hwang.

So, please come see the festival up in Manchester this Autumn. But before then, if you can, please consider donating to the cause and help make TimeWave happen.

Having been healthy and not particularly accident-prone, this was the first time since age 6 or so that I’ve been to the hospital for myself, although I’ve accompanied or visited a few friends and loved ones over the years. Britain’s NHS is, of course, a remarkable institution: universal health care with outcomes that are overall as good as the much more expensive American system. But that very size means that patients don’t always get exactly the treatment they might like.

Before heading to the doctor that morning, a few minutes online indicated that I probably had something like insertional Achilles tendinitis, a pretty common complaint especially amongst runners. My GP couldn’t help much, but got much the same information from the computer on her desk, and decided that it required more work — possibly a cast — than she could handle there.

So after hobbling over to Charing Cross hospital, relatively nearby in London (and nowhere near Charing Cross), I was told to sit and wait, possibly for about two hours — and I was a lucky one, having come with a doctor’s note enabling me to skip the triage step and get directly on the list. So a couple of hours later, I finally made it in to see someone, a very nice nurse practitioner. I was surprised, however, when he looked at my heal and said that he had never seen anything like that before. He waved a nearby doctor into the examination room, but the latter clearly just wanted to go home after a long shift, and didn’t have much to add beyond the frankly strange suggestion of a “foreign body”. The pair were about to send me in for an x-ray when another nurse practitioner walked by, looked down, and said, “oh, that’s bursitis”, an inflammation of the bursa, the sac of fluid which keeps the joint between the tendon and the bone lubricated. This seemed altogether more plausible (although a condition I tend to associate with my now-101-year-old grandmother). And, fortunately or otherwise, the suggested treatment was just ice, anti-inflammatory painkillers, and rest. To facilitate the latter, I got a new pair of accessories, pictured at right (taken at my local, hoping that alcohol was not contraindicated).

As a not-terribly-old, not-terribly-infirm, male, I am used to deferring to pretty much everyone except teenagers for positions on lines (queues) and seats on public transport. So the crutches work a weird psycho-physical magic on me and the people around: lots more saying “sorry”, getting up or moving out of the way for me. I don’t like it.

Things are, happily, looking up. I can walk only a bit asymmetrically and without too much pain (and without the crutches for the last day or so). Let’s hope I’m running again before my next half-marathon.

Statistics and astronomy have a long history together, largely growing from the desire to predict the locations of planets and other heavenly bodies based on inexact measurements. In relatively modern times, that goes back at least to Legendre and Gauss who more or less independently came up with the least-squares method of combining observations, which can be thought of as based on the latter’s eponymous Gaussian distribution.

Our group had already had a much shorter but still significant history in what has come to be called “astrostatistics”, having been involved with large astronomical surveys such as UKIDSS and IPHAS and the many allowed by the infrared satellite telescope Herschel (and its predecessors ISO, IRAS and Spitzer). Along with my own work on the CMB and other applications of statistics to cosmology, the other “founding members” of ICIC include: my colleague Roberto Trotta who has made important forays into the rigorous application of principled Bayesian statistics to problems cosmology and particle physics; Jonathan Pritchard who studies the distribution of matter in the evolving Universe and what that can teach about its constituents and that evolution; and Daniel Mortlock, who has written about some of his work looking for rare and unusual objects elsewhere on this blog. We are lucky to have the initial membership of the group supplemented by Alan Heavens, who will be joining us over the summer and has a long history of working to understand the distribution of matter in the Universe throughout its history. This group will be joined by several members of the Statistics section of the Mathematics Department, in particular David van Dyk, David Hand and Axel Gandy.

One of the fun parts of starting up the new centre has been the opportunity to design our new suite of glass-walled offices. Once we made sure that there would be room for a couple of sofas and a coffee machine for the Astrophysics group to share, we needed something to allow a little privacy. For the main corridor, we settled on this:

The left side is from the Hubble Ultra-Deep field (in negative), a picture about 3 arc minutes on a side (about the size of a dime or 5p coin held at arm’s length), the deepest — most distant — optical image of the Universe yet taken. The right side is our Milky Way galaxy as reconstructed by the 2MASS survey.

The final wall is a bit different:

The middle panels show part of papers by each of those founding members of the group, flanked on the left and right side with the posthumously published paper by the Rev. Thomas Bayes who gave his name to the field of Bayesian Probability.

Of course, there has been some controversy about how we should actually refer to the place. Reading out the letters gives the amusing “I see, I see”, and IC² (“I-C-squared”) has a nice feel and a bit of built-in mathematics, although it does sound a bit like the outcome of a late-90s corporate branding exercise (and the pedants in the group noted that technically it would then be the incorrect I×C×C unless we cluttered it with parentheses).

We’re hoping that the group will keep growing, and we look forward to applying our tools and ideas to more and more astronomical data over the coming years. One of the most important ways to do that, of course, will be through collaboration: if you’re an astronomer with lots of data, or a statistician with lots of ideas, or, like many of us, somewhere in between, please get in touch and come for a visit.

Unfortunately we don’t yet have a webpage for the Centre..

Roman was a Polish cosmologist who began his career in the Russian school, working with Ya. Zeldovich, probably the most eminent Soviet cosmologist and astrophysicist of the 20th Century. Roman himself went on to work in Paris, Berkeley, Geneva, Princeton, and of course back in Poland in both Warsaw and more recently in Zielona Gora, always doing his best to find friends and collaborators in places worth a visit.

He specialised in trying to understand the growth of structures in the universe. I was lucky enough to work with him on a series of papers over the last decade and a half, mostly examining how the motions of galaxies respond to the distribution of matter, and how we can use that to measure the total density of matter. Most recently, in one of Roman’s very last papers, we tried to clear up some confusion about the relationships amongst different ways of measuring and describing the clustering of the matter and of the galaxies that we directly observe.

As much as I will remember and miss Roman as a collaborator, I and most of his friends will surely miss him even more as a companion: Roman liked to enjoy his friends’ company as much over food and wine as over a good scientific discussion. Ideally, of course, we managed both at the same time, often well into the night and leaving many empty bottles and plates behind.

Tonight, I will try to leave at least a couple of empty glasses behind in Roman’s memory and honour.

(If instead you’d prefer something a little more tutorial, I can recommend the excellent recent post from my colleague Ted Bunn, discussing hypothesis testing, stopping rules, and cheating at coin flips.)

Deborah Mayo has begun her own series of posts discussing some of the articles in a recent special volume of the excellently-named journal, “Rationality, Markets and Morals” on the topic Statistical Science and Philosophy of Science.

She has started with a discussion Stephen Senn’s “You May Believe You are a Bayesian But You Are Probably Wrong”: she excerpts the article here and then gives her own deconstruction in the sequel.

Senn’s article begins with a survey of the different philosophical schools of statistics: not just frequentist versus Bayesian (for which he also uses the somewhat old-fashioned names of “direct” versus “inverse” probability), but also how the practitioners choose to apply the probabilities that they calculate: either directly in terms of inferences about the world versus using those probabilities to make decisions in order to give a further meaning to the probability.

Having cleaved the statistical world in four, Senn makes a clever rhetorical move. In a wonderfully multilevelled backhanded compliment, he writes

If any one of the four systems had a claim to our attention then I find de Finetti’s subjective Bayes theory extremely beautiful and seductive (even though I must confess to also having some perhaps irrational dislike of it). The only problem with it is that it seems impossible to apply.

He discusses why it is essentially impossible to perform completely coherent ground-up analyses within the Bayesian formalism:

This difficulty is usually described as being the difficulty of assigning subjective probabilities but, in fact, it is not just difficult because it is subjective: it is difficult because it is very hard to be sufficiently imaginative and because life is short.

And, later on:

The … test is that whereas the arrival of new data will, of course, require you to update your prior distribution to being a posterior distribution, no conceivable possible constellation of results can cause you to wish to change your prior distribution. If it does, you had the wrong prior distribution and this prior distribution would therefore have been wrong even for cases that did not leave you wishing to change it. This means, for example, that model checking is not allowed.

I think that these criticisms mis-state the practice of Bayesian statistics, at least by the scientists I know (mostly cosmologists and astronomers). We do not treat statistics as a grand system of inference (or decision) starting from single, primitive state of knowledge which we use to reason all the way through to new theoretical paradigms. The caricature of Bayesianism starts with a wide open space of possible theories, and we add data, narrowing our beliefs to accord with our data, using the resulting posterior as the prior for the next set of data to come across our desk.

Rather, most of us take a vaguely Jaynesian view, after the cranky Edwin Jaynes, as espoused in his forty years of papers and his polemical book Probability Theory: The Logic of Science — all probabilities are conditional upon information (although he would likely have been much more hard-core). Contra Senn’s suggestions, the individual doesn’t need to continually adjust her subjective probabilities until she achieves an overall coherence in her views. She just needs to present (or summarise in a talk or paper) a coherent set of probabilities based on given background information (perhaps even more than one set). As long as she carefully states the background information (and the resulting prior), the posterior is a completely coherent inference from it.

In this view, probability doesn’t tell us how to do science, just analyse data in the presence of known hypotheses. We are under no obligation to pursue a grand plan, listing all possible hypotheses from the outset. Indeed we are free to do ‘exploratory data analysis’ using (even) not-at-all-Bayesian techniques to help suggest new hypotheses. This is a point of view espoused most forcefully by Andrew Gelman (author of another paper in the special volume of RMM).

Of course this does not solve all formal or philosophical problems with the Bayesian paradigm. In particular, as I’ve discussed a few times recently, it doesn’t solve what seems to me the most knotty problem of hypothesis testing in the presence of what one would like to be ‘wide open’ prior information.

Planck’s High-Frequency Instrument (HFI) instrument must be cooled to 0.1 degrees above absolute zero, maintained at this temperature by a series of refrigerators — which had been making Planck the coldest known object in space, colder than the 2.7 degrees to which the cosmic microwave background itself warms even the most regions of intergalactic space. The final cooler in the chain relies on a tank of the Helium-3 isotope, which has finally run out, within days of its predicted lifetime — and giving Planck more than twice as much time observing the Universe as its nominal 14-month mission.

The Low-Frequency Instrument (LFI) doesn’t require such cold temperatures, although in fact they do use one of the earlier stages in the chain, the UK-built 4-degree cooler, as a reference against which it compares its measurements. LFI will, therefore, continue its measurements for the next half-year or so.

But our work, of course, goes on: we will continue to process and analyse Planck’s data, refining our maps of the sky, and get down to the real work of extracting a full sky’s worth of astrophysics and cosmology from our data. The first, preliminary, release of Planck data happened just one year ago, and yet more new Planck science will be presented at a conference in Bologna in a few months. The most exciting and important work will be getting cosmology from Planck data, which we expect to first present in early 2013, and likely in further iterations beyond that.

I have been lucky enough to meet Stephen, and was even invited to a dinner party at his house, where I got to see him posing with his Presidential Medal of Freedom, awarded by Barack Obama in 2009. So I was especially disappointed to subsequently hear that he was too ill to actually attend his conference in Cambridge. I wish him a very Happy Birthday and a speedy recovery.

It’s not hard to talk about Hawking: he’s been involved with some truly exciting breakthroughs in theoretical physics over the last few decades, perhaps most importantly for teasing out the relationship between the properties of black holes and the laws of thermodynamics. This seemingly formal analogy was realized to be much more than that with Hawking’s discovery that black holes are not, in fact, “black” — rather, they glow at a temperature inversely proportional to the mass of the black hole, emitting what has come to be called Hawking Radiation.

These are very significant discoveries, teaching us something crucial about the connections between the three great theories of physics, quantum mechanics, gravity and thermodynamics. But it’s safe to say that no one yet fully understands exactly what those relationships are.

And of course Hawking’s nonscientific accomplishments are well-known and justly valorised. He has lived with — triumphed over — ALS for far longer than any of his doctors had predicted. He has written one of the best-selling popular science books of all time, A Brief History of Time. And, needless to say, he’s done some amazing scientific work, just some of which I’ve mentioned above.

There have been very many very brilliant physicists through the centuries. So it would certainly be premature, if not churlish, to take the long view and ask where Hawking would sit in the pantheon of physicists from Archimedes through Newton, Einstein and beyond. Indeed, as my friend and colleague Peter Coles has just written, Hawking’s peers have so far decided that the time is not yet ripe to elevate him to the top of the table. (Peter has also written a short book on the subject, picking apart some of the interactions between scientists, the media and the wider public.)