Saturday, 30 June 2007

Off to Spain

OK, I'm off bright and early tomorrow to Spain, to spend a week complaining about the heat. I'll try and post some photos, if I can get time.

Until then, on the off-chance that someone reading this hasn't read it already, GrrlScientist has a wonderful post up about trans-Arctic dispersal in the rubber duck. She's been very kind and helpful with advice already, so go along and take a look. And if you're in the UK, make a note of what the ducks look like - you may meet one on a beach some day. Read more!

Friday, 29 June 2007

The Royal Society Of London has just sent out the Table of Content for Proc. R. Soc. B. It includes this:

Genetic analysis reveals promiscuity among female cheetahs
p. 1993
Dada Gottelli, Jinliang Wang, Sultana Bashir, Sarah M. Durant

URL of article:
Some puns just shout so loudly, you have to ignore them. Need I say more?

Actually, I will: Vesa, my former office-mate has a paper in there too. Flying squirrels - cuter but less important than Harry Potter. Read more!

Wednesday, 27 June 2007

Oh, the irony

So, the big British political news this morning was the defection of a Tory MP to Labour.  As part of his resignation letter, Quentin Davis wrote

Under your leadership the Conservative party appears to me to have ceased collectively to believe in anything, or to stand for anything.

It has no bedrock. It exists on shifting sands. A sense of mission has been replaced by a PR agenda.


Although you have many positive qualities you have three, superficiality, unreliability and an apparent lack of any clear convictions, which in my view ought to exclude you from the position of
national leadership to which you aspire...

Is it just me, or is this, particularly the last part ironic on the day that Tony Blair resigned?  We were hearing exactly the same things about him 10 years ago.

When did Peter Mandelson defect in the other direction?

Read more!

Tuesday, 26 June 2007

The Big Harry Potter prediction

I was (re-)writing a lecture for a course I'm giving next week in Asturias, and included an example of prediction.  I thought it was sufficiently interesting to preview here.  Feel free to disagree.

The background: even if you haven't heard now, you'll soon be sick of hearing that HP7, Harry Potter and the Deadly Hallows is released next month.  There are lots of unknowns, which give us plenty of scope to predict what will happen, and then hope nobody remembers when they're wrong.

So, I decided to make my own predictions - after all, that is what the lecture is about.  So, I've tried to predict how many pages the book will have.  As the course is in statistics, we need data.  For that I use the number of pages in the previous books, and the dates they were published:

Potter book lengths

Odd, it looks like Ursa Major.  It must be a clue!  Perhaps it's pointing north, so Harry will have to go to the frozen northlands, be helped by a polar bear in his quest, and in the final climax end up betraying a friend in order to save everything, and break through to a new universe.


Anyway, now we do a linear regression.  Because the course is about Bayesian analysis, I did a Bayesian prediction.  This meant firing up BUGS, fitting a straight line, and predicting the number of pages for a Harry Potter book published in 2007.  I also made a prediction based on the least squares estimate of the line.  This is what I got:

HP7 pages prediction

The thick bars are +/-one standard error, the thin bars are the 95% confidence/credible intervals.  Next week I will blather on about why the Bayesian intervals are wider, but for the moment, I want to point out that I'm predicting that HP7 will be about 860 pages long, but with a wide margin of error: there's a 95% probability that it will be between 500 and 1200 pages long.

And I get paid to do this stuff.

Read more!

Monday, 25 June 2007

OpenBUGS3.0.1 released

Of the many "it seemed like a good idea at the time" things I have done in my life, one was to volunteer to set up the OpenBUGS pages.  I did this in the spirit of helping out, rather than one of showing off my html skills (I hope this is obvious from the pages).  Nowadays this mainly means transferring a zip file from a memory stick to our we server, and then checking I haven't broken anything.  The real programming work is done by Andrew Thomas, so he's the one who should get all the thanks now.

Anyway, as you might have guessed from the title, I've just put version 3.0.1 of OpenBUGS up on the web.  Actually, this is a slight cheat - I put a version up a couple of weeks ago, and then we promptly found a couple of bugs/features.  Andrew solved both of them, although one solution is geopolitical - giving the Åland islands back to Sweden.

The good news about the changes is that it gave Andrew more time to work on the BUGS to LaTeX language converter, ably supported by Mikko Sillanpää.  Of course, the first thing I tried with it was throwing some of my more complex models at it, but it seems to manage.  For example, here is what the LaTeX code produces for this paper:

OK, it's not perfect (and looks better on its own: bits are disappearing off the edge of the window) but it is fairly easy to edit the LaTeX code.  There are also a few changes to the BUGS code that would make it more readable (e.g. writing tau.S, rather than tauS, so that BUGS recognises the tau).  Overall, I'm impressed, and suspect I'm going to drift even deeper into the clutches of LaTeX now.

So, I'm happy for a bit - even if I should be doing N other things this week.

Read more!

Sunday, 24 June 2007

Hello World!


*tap tap*

Is this thing on?  

Hmmm, I wonder what this button does.


I won't try that again for a bit.

Err, hello. After wandering the blogosphere for some time, and mugging posts with silly comments and games of Mornington Crescent, I finally decided to create my own blog, so I could pontificate on the world.

For anyone who doesn't know me, I'm an Englishman who has drifted to Finland, and now work at the University of Helsinki as a researcher, in statistics, ecology, evolutionary biology and such things.  I have mainly been hanging round the science blogs, so I'll probably post on these matters, but there will also be other things that take my fancy as well (like possible uses for cat hair). 

OK, now I have to think of something to write about.

Read more!