Proceedings CD

Plenaries

Plenary 1: What showbiz has to do with it

Hans Rosling

If you show the core numbers of statistics, rather than the meaning of the data, your audience will be small.

Just imagine what would happen if you climb the stage in a concert hall just to show a PowerPoint presentation of the musical notes of a famous piece. Even if it is from a great composer you will not get a standing ovation. Neither will you if you just display a newly constructed musical instrument to the audience. The success in music depends on a great composition being played on a good musical instrument that fits the composition by a musician that adds his personal interpretation but sticks to the notes of the composer. This is my vision for statistics. Get the great data sets with time series compiled by professional statisticians, let the IT industry develop new instruments for animated graphic displays, and then develop a new strain of statistical musicians. In other words just as meteorologists are doing every evening on prime time TV with their data. And those meteorologists with show biz talents become like rock stars in many countries.

By serendipity Gapminder Foundation found that the beauty of a statistical database can be unveiled to a broad audience if the data set can be animated in newly developed software. Many things are needed and the last step is a presenter who manages to display the dataset in that software in a way not too different from how a musician can unveil the beauty of a composition. The value of a statistical database depends on how widely it can be used and understood and that in its turn depends on whether the database is made available in a uniform and machine readable format to faster innovation of graphical data display. Animated displays of time series do not replace any other form of data presentation. Its aim is to attract new user groups to the beauty of statistics. I will review what it will take to bring statistical databases into prime time TV.

Paper

Plenary 2: The strength of evidence versus the power of belief: are we all Bayesians?

Jessica Utts

Although statisticians have the job of making conclusions based on data, for many questions in science and society prior beliefs are strong and may take precedence over data when people make decisions. For other questions, there are experts who could shed light on the situation that may not be captured with available data. One of the appealing aspects of Bayesian statistics is that the methods allow prior beliefs and expert knowledge to be incorporated into the analysis along with the data. One domain where beliefs are almost sure to have a role is in the evaluation of scientific data for extrasensory perception (ESP). Experiments to test ESP often are binomial, and they have a clear null hypothesis, so they are an excellent way to illustrate hypothesis testing. Incorporating beliefs makes them an excellent example for the use of Bayesian analysis as well. In this paper, data from one type of ESP study are analyzed using both frequentist and Bayesian methods.

Paper

Plenary 3: Helping doctors and patients make sense of health statistics: towards an evidence-based society

Gerd Gigerenzer

Collective statistical illiteracy is the phenomenon that the majority of people do not understand what health statistics mean, or even consistently draw wrong conclusions without noticing. For instance, few are aware that higher survival rates with cancer screening do not imply longer life, or that the statement that mammography screening reduces the risk of dying from breast cancer by 20% in fact means that 1 less woman out of 1,000 will die of breast cancer. I argue that statistical illiteracy (i) is common to patients, journalists, and physicians alike; (ii) is created by nontransparent framing of information that is sometimes an unintentional result of lack of understanding, but can also be an intentional effort to manipulate or persuade people; and (iii) is a consequence of the ongoing lack of efficient training in statistical thinking in the educational system.

Paper

Plenary 4: Unifying graduate statistics: a big umbrella for a small country

Anuška Ferligoj

Slovenia, as a small country, has limited human resources. Eight years ago statisticians active in the Statistical Society of Slovenia established the country’s first university graduate program on statistics. It included biostatistics, mathematical statistics, official statistics and social statistics modules. The program was quite successful and became extremely important for statistical education and research in Slovenia. Recently, all university programs had to be reformed according to the Bologna principles. In renewing the doctoral statistical program, we added three new modules: economic and business statistics, psychological statistics and technical statistics. The interest expressed by other departments and faculties for inclusion in this doctoral program of statistics emphasizes both the original need for such a graduate program of statistics and its success.

Paper

Plenary 5: The Great Debates of ICOTS 8

Helen MacGillivray, Queensland University of Technology, Australia
Chris Wild, University of Auckland, New Zealand

Participants
Dani Ben Zvi, Adrian Bowman, Rob Gould, Irena Ograjensek
Enriqueta Reston, Eric Sowey, Susan Starkings, Linda Young

Propositions to be debated

• Formal statistical inference has no place in high school curriculums
• Researching is more fun than teaching

These debates will be modelled on the style of debating in use in English-speaking schools and universities, but with relaxed rules. It is a competitive team sport. For each proposition, one team (the “affirmative team”) will try to make a convincing case that the proposition is true, whereas the other team (the “negative team”) will try to argue for the opposite.

Plenary 6: The virtues of building on sand

Cliff Konold

Ten years ago we began developing TinkerPlots, a data-analysis tool for young students. The premise that guided our design was that the software should allow young students to accomplish goals that made sense to them, using operations that they understood. Having succeeded in doing this, the challenge then became figuring out how to build on this “foundation of sand” so as to move novices towards expertise.

I will describe our recent efforts to design capabilities such as smoothed average fits of bivariate data and residual analyses by working up from capabilities and operations that novices perform with understanding. Results of testing these in classrooms suggest that students begin to incorporate new statistical tools and ideas into their repertoire by initially using them in conjunction with their existing, often limited, tool set.

Paper