Hug the math

These cushions are truly cute and would make a memorable lecture on probability distributistatistical-distribution-plushiesons for sure! The original post about them is here. They are:

  • Baby Blue t Distribution
  • Light Pink Log Normal Distribution
  • Lilac Continuous Uniform Distribution
  • Tan Weibull Distribution
  • Olive Green Cauchy Distribution
  • Slate Blue Poisson Distribution
  • Maroon Gumbel Distribution
  • Gray Erlang Distribution
Comments Off on Hug the math

Mobile phone security threats and how to defend against them

Henry Wolfe of the University of Otago certainly knows how to put the wind up a bunch of students and staff! His talk on 6 November about threats to mobile phone security covered the whole range from signal jammers and fake mobile phone towers to how to turn your phone into a bugging device. On the defence side, he showed us all how to find the International Mobile Equipment Identity of your phone (look under the battery or text *#06#) and offered sound advice on turning off tool such as Bleutooth and Near Field Communication when not in use. On the other hand I think the jury is still out on the relationship between mobile phone use and brain cancer – some weekend reading perhaps!

Comments Off on Mobile phone security threats and how to defend against them

Prediction of biogeographical ancestry from genotype: a comparison of classifiers

On 6 November there was quite a festival of presentations from Honours students in Forensic Science here at UC. I attended Elaine Cheung’s presentation, first thing in the morning.

She had carried out a very nice investigation into three classifiers – Bayesian, genetic distance, and multinomial logistic regression – for identifying biogeographical ancestry from SNP data. She manipulated the degree of missing data and the number of SNPs analysed to complete her experiment. Her ROC curves were in many cases very close to perfect, and she made the interesting decision to swap to reporting area OVER the curve instead of UNDER the curve to highlight the results of interest. I think there’s another whole Honours project in Stats, about the behaviour of the area OVER the ROC curve!

Comments Off on Prediction of biogeographical ancestry from genotype: a comparison of classifiers

I think you’ll find it’s a bit more complicated than that

I have enjoyed reading this collection of newspaper columns by Ben Goldacre. He was awarded the Royal Statistical Society prize for journalism a few years ago, and his writing about bad science, bad pharma and so on is very entertaining. His message remains the same throughout – the importance of staying true to statistical principles when reporting on scientific breakthroughs.

Comments Off on I think you’ll find it’s a bit more complicated than that

Enhancing the spoken ability of Saudi second language Learners of English using the somatically-enhanced approach

This seminar was given by Ibrahim Alturki on 28 October to confirm his PhD candidature. Clapping, humming, gestures and body movements – it makes a language learning class sound like a music theory class or a choir rehearsal, I love it! This will be the first use of the somatically-enhanced approach to teach English, as opposed to tonal languages such as Mandarin and Thai.

Comments Off on Enhancing the spoken ability of Saudi second language Learners of English using the somatically-enhanced approach

World Statistics Day 2015

Happy World Statistics Day everyone! This year I arranged for a small poster display in the Refectory – thanks to the American Statistical Association in 2009 for producing those great posters about statistics in various disciplines. I also rounded up half a dozen colleagues to staff a chat-to-a-statistician desk in the central admin area of the University – next to a very popular little coffee shop.


Comments Off on World Statistics Day 2015

The future of big data science

Dr Damjan Vukcevic from the Murdoch Childrens Research Institute in Melbourne addressed the Young Statisticians meeting of the Statistical Society on 13 October. His career has spanned three very different organisations – from the University of Oxford to Experian, a web analytics company, to the health research institute where currently works.

Damjan told us about the characteristics of the projects he has worked on involving large data sets , from massive genome-wide association studies to hierarchical Bayes clustering with informative priors. His parting message to young statisticians was to get involved – in anything from hackathons to Open Knowledge Australia to Kaggle. he also impressed upon the young statisticians present that frequently a robust answer beats an optimal one – a notion which I recall as a student somewhat horrified me, but as an experienced statistician and statistical engineer I completely agree!

Comments Off on The future of big data science

Ada Lovelace Day 2015

This year the University of Canberra celebrated Ada Lovelace Day on 13 October with a breakfast for women in STEM, hosted by the women in Arts. They had been doing some fantastic work connecting STEM and A (making STEAM) as the right hand side of the photo shows. It’s a knitted piece inspired by the patterns of plugs and cables on the hybrid digital-analogue computer owned by the Faculty of ESTeM. There were also wooden brooches with similar circuitry-inspired pokerwork.

AdaLovelaceDay2015 compress


Comments Off on Ada Lovelace Day 2015

Rethinking how we teach statistics from the ground up

Food for thought on a Friday morning. George Cobb, that excellent statistics educator, wrote an opinion piece for the Royal Statistical Society in August (you can find it here). His five imperatives for rethinking statistics teaching, from the ground up, were


  • Flatten prerequisites
  • Seek depth
  • Embrace computation
  • Exploit context
  • Teach through research


We’ve certainly pursued the first of these here at the University of Canberra, and the last is in fact a signature theme of the whole University. I think we’ve got a bit of work to do on the middle three, particularly around the tension between pursuing depth when small student numbers are involved. We’re in for an exciting time!

Comments Off on Rethinking how we teach statistics from the ground up

Time for innovative teaching

James Arvanitakis, Professor of Humanities and Dean of the Graduate School at University of Western Sydney, and University Teacher of the Year, gave this interactive presentation on 3 September. He describes himself as an academic generalist and told us a couple of funny anecdotes about his own first days at University. Then he moved on to his main message – that universities are no longer the custodians of content, but are in direct competition with organisations such as Wikipedia. He described how in his own unit, Introduction to Sociology with 1000+ students, he doesn’t teach content, but teaches how to apply it to everyday life. His lectures typically start with an application (a video, a news story), then get on to the theory.

James encouraged us to think about planning a unit both at the semester level and the unit level. Semester planning could even mean starting at the end of the unit and thinking about how to get there. He encouraged us to have a semester-long story arc in the back of our minds for each unit. At the lecture level, James reminded us that 4 mini-lectures of 15 minutes will help to keep the attention levels up.

I was amused at the fun questions he gets his sociology students to tackle – the weight of the Harbour Bridge, how many chips are eaten at the MCG, and so on. These questions are highly numerate and statistical in nature and I’d like to think that my students would handle them really well.

In conclusion James encouraged us to model what we wanted out students to be like – and I believe I do demonstrate what I want my students to be. Fascinated, excited, competent, statistically literate.

Comments Off on Time for innovative teaching