Saturday, 12 March 2011

Cas Troskie

Cas Troskie
My book Biplots in Practice (see later below) is dedicated to Cas Troskie, who passed away earlier this year.  In the preface of my book I wrote the following: 

"This book is appropriately dedicated to Prof. Cas Troskie, former head of the Department of Statistical Sciences at the University of Cape Town (UCT), South Africa, and a maestro of theoretical and applied multivariate analysis.  Cas was one of the most influential people in my statistical career, in fact when he visited me on Barcelona on several occasions I always introduced him as the reason behind my decision to do Statistics as a major in my initial Bachelor of Science studies at UCT.  As early as 1969, aged 33 and the youngest department head on the UCT campus, he was encouraging students like myself to write computer programs and put decks of punched cards into card readers linked to the university computer and wait expectantly for printouts to emerge with the results.  He had a singular faith in principal components of a data set, which prepared me for my subsequent studies in France on correspondence analysis.  I am not alone in being affected by his dynamic personality and sharp intelligence, since he inspired dozens of Masters and PhD theses, leaving a huge legacy to the statistical community, not only in South Africa but worldwide."

Wednesday, 9 March 2011

you, woman

It's more than 10 years since Gurdeep Stephens and I recorded this album of my compositions, with our friend Santi Careta doing a great job as recording engineer as well as filling in with beautiful additional guitar riffs.  The lyrics of half of the songs (see the full list here) are poems written by my friend, André de Wet — photographer, poet, artist and sculptor — and the album will always remain a tribute to his memory.  Here you can hear Gurdeep singing the theme song "you, woman", written by André, myself on Spanish guitar and Santi on electric guitar:

Statistical songs

I've written several songs at conferences and workshops, often based on an existing song. For example, It Don't Mean a Thing (if you ain't got that swing), by Duke Ellington, turned out to be It Don't Mean a Thing (if you don't do modelling), sung by Gurdeep Stephens at the opening of the International Workshop on Statistical Modelling, in Barcelona, July, 2007:

    It don't mean a thing if you don't do modelling,
    It don't matter if you're frequentist or Bayesian,
    You just need a model with some alphas and betas, x's and y's, and i's and j's and k's in,
    So it don't mean a thing etc...

You can find this and many more (It Ain't Necessarily So, The Model I Love and Summertime) sung by the inimitable Gurdeep Stephens at

A more recent one was at the 6th CARME conference, held in Rennes in February 2011. CARME stands for "Correspondence Analysis and Related Methods" and is also a Catalan woman's name, so I really wanted to make a song for this event. A doctoral student in statistics, Yuna Blum, who sings in a rock group in Rennes, agreed to sing them at the conference dinner. Here she is singing CARME on my Mind:

You can also hear Yuna singing CARMEtime at, and she also did two French songs, Les Feuilles Mortes and Bambino which you can find at

Monday, 7 March 2011

My book on biplots

Now for something scientific but which is equally "moving": visualizing data through biplots.  A biplot is simply an extension of what statisticians call a scatterplot.  A scatterplot plots two variables, often called x (the horizontal axis of the plot) and y (the vertical axis).  A biplot includes many variables at the same time, but because it is trying to show many relationships at the same time, it compromises by showing the data approximately as best it can.  Opposite you will see the cover of my book, published in 2010, on this subject.  The book was published by the BBVA Foundation in Madrid, with excellent production by Rubes Editorial in Barcelona.  The book is sold without profit and is also available online for free download at the website

Now how can one method like this fill a whole book?  It is simply because there are many different types of data in research: quantitative data, qualitative data, data on a scale of percentages, and so on, and each data type poses a different challenge for the way it is turned into a biplot.  A novel aspect of the book is that the associated website mentioned above also contains videos which illustrate the concepts in the book.  Here are two for a start:

Video showing a three-dimensional view of a set of points (countries measured on three economic indicators). At one point the country points almost line up, showing that the three-dimensional configuration is approximately two-dimensional. The rotation spreads out the configuration of points, pausing at that two-dimensional view. (Since one's eye can flip between seeing a regular cube and a distorted one, try to keep the "Purchasing power" axis at the back, away from you.

Video showing a set of points where the vertical variable (abundance of a marine species, denoted by d) is assumed to depend on the other two, pollution and depth. The so-called regression plane is shown, which best fits the points and so summarizes the functional relationship approximately. (The rotation should be seen to be counter-clockwise.)

The Millennium Song

Cover of the CD of The Millennium Song,
published by the Universitat Pompeu Fabra
Dove of Peace stained glass by Leo Theron
Eleven years after we recorded the Catalan video of The Millennium Song ("La Cançó del Mil·lenni") in December 1999, I have finally uploaded it to youtube at "YouWomanGroup" — you can see and listen to it below.  I wrote the English lyrics of this song on the theme of Chopin's prelude op.28 no.20 in C minor (originally intended as a funeral march, but which becomes distinctively re-born in my arrangement!). Then a colleague at the Universitat Pompeu Fabra (UPF) Anna Asian translated it into Catalan, and a friend Merché Bellido made the Spanish version, with the idea starting to develop into a full-time project.  The UPF rector at the time, Enric Argullol, liked the multicultural aspect and decided to publish a CD of the song as the university's official 10th anniversary gift (above): in English and the four languages of Spain — Spanish, Catalan, Basque and Galician.
Gurdeep Stephens
Bronwen Forbay
Gurdeep Stephens recorded all these versions as well as the Norwegian and Occitan translations.  My friend Volker Hooyberg and his son Nicholas organized that Sibongile Khumalo — without a doubt, South Africa's most famous singer — record the Zulu translation.  Volker also involved an up and coming South African opera singer, Bronwen Forbay, to record the Afrikaans and German translations. A Slovenian version was recorded in Ljubljana by Nuška Drašček.  The backing tracks of the song were recorded by the Santi Careta Group.
Nuška Drašček


Sunday, 6 March 2011

How to win a "spark" race in Norway

"Spark" in Norwegian means "kicks", and a spark is a kicksled, a clever Norwegian invention shown here.
A BBC reporter took part in the world kicksled championships in Norway and the report is not only amusing but also has a game-theoretic aspect that might appeal to my colleagues at the UPF.  Listen to the clip below to hear why it is quite OK to stop along the way during the race and have a couple of drinks at a bar - this will possibly be the key to your winning the race!

Arctic Frontiers 2011: "Tipping Me Softly"

The conference ARCTIC FRONTIERS in Tromsø, January 2011, had the theme Arctic Tipping Points. I made a collage of word clouds for the introduction and coffee breaks at the conference and also a conference song, called "Tipping Me Softly", which you can see in the videos below.

"Tipping Me Softly" was sung here for the first time by my daughter Karolien on board the Norwegian coastal ferry M/S Midnatsol, taking students of the Young Scientist Forum from Tromsø to the Lofoten Islands -- there was no lighting on the stage, so the video (taken with a friend's iPhone) is rather dark, but the words can be heard clearly:

I am the Arctic beauty
Of land and ice and sea,
I lived for ages
When all was harmony.
But in just hundred years
I feel man coming closer...

Changing my state with pollution
Melting my ice burning coal
Tipping me softly to the point,
Tipping me softly to the point,
Turning my whole life to this state,
Tipping to this point of no return.

I felt all flushed with fever,
My climate turning warm,
I've never had so much heat
Since the earth was born!
I give you all my data,
And ask you to save me from...


Science magazine's special data issue

The magazine Science has a special issue "Dealing with Data" in February. In their podcast there's a fascinating description of the amount of information circulating in digital form now compared to the amount of information in nature.  Listen to it here: