CEOs, Presidents and National Leaders of Australia’s major mathematical-based societies* united in a consortium through 2018 to submit (October 2018) a bid for Australia’s hosting of the 15th International Congress on Mathematical Education (ICME15), 2024, at the International Convention Centre, Sydney, Australia, and then hosted the ICMI delegates’ site visit in April 2019; at the time we were one of two shortlisted locations, the other, Prague.

ICME is run once every four years and was last hosted in Australia in 1984. I have been representing the Statistical Society of Australia in this consortium.

As a member of the national consortium, I’m delighted to share the exceptional news that our collaborative bid for Australia (Sydney) to host the International Congress on Mathematical Education in 2024 has been successful.

A wonderful team effort that united Australia’s leading mathematical and statistical associations* - thank you to those who supported the consortium’s bid.

Please help spread the good news as we continue the cooperative initiative and begin preparing for 2024 and ensuring that the national Mathematical/Statistical and broader STEM agenda are further capitalised upon on the international stage.

* AMSI, AAMT, SSA, ATSIMA, ACHMS, MANSW, MERGA & UNSW, USyd, UoN, UTS, WSU, NESA

Peter Howley, Statistical Education Section – Chair

With the Federal Election looming, everyone’s focus is very much on Canberra at this time, but there is another reason our minds should turn tothe nation’s capital: The Young Statisticians Conference 2019 is just around the corner!

There is so much to look forward to! For starters, we are just delighted with this year’s choice of venue: Manuka Oval. With a rich and diverse history, stunning views across the lawns and being close Canberra’s popular restaurant strip Manuka, this iconic meeting place will be sure to impress.

As it happens, this year the conference coincides with Floriade, Canberra’s annual flower show - a colourful celebration of Spring.Click here to see what it’s all about.  Be careful though – there will be so much on that you may get too distracted from attending the conference!

The YSC2019 Committee is doing an excellent job of getting everything ready for you and they now have four wonderful key-note speakers lined up:

Teresa Dickinson
Deputy Australian Statistician, Australian Bureau of Statistics

Dr Margarita Moreno-Betancur
Senior Research Fellow, VicBiostat

Dr Felicity Splatt
Lead Consultant, Quantium

and

Dr Alison Presmanes Hill
Data Scientist & Professional Educator, RStudio

Alison will arrive a day early and present a pre-conference workshop.

Not coming to the conference? Don’t worry – you still get to participate if you want to. We are pleased to invite anyone who can’t be there in person to share their research through the YSC2019 Video Competition. This competition ran for the first time at YSC2017 and it was so successful that of course we had to organise it again!  Click here to see the winning entries from YSC2017. 

To throw your hat in the ring, just present your research in a three-minute video and submit the link through the online registration form.

For those of you who are planning to be there in person, why not combine your trip to the conference with a little holiday? You’ll have the chance to explore one of Australian’s most beautiful cities, and to experience Australian culture and history at superb monuments and galleries. Canberra is a city surrounded by parkland and native bush and Spring is the perfect time for a visit. If this hasn’t convinced you, Channel Nine’s “Travel Guides” might do so.

Some key dates to keep in mind:

Abstract submission closes -1 June 2019 Notification of conference abstract acceptance – 1 July 2019 Early bird registration period ends – 16 August 2019 Three-minute video competition submissions due – 15 September 2019 Conference registrations close – 17 September 2019 Monday 1 July	Saturday 1 June

See you in Canberra in October!

Marie-Louise Rankin
SSA Executive Officer

On 30 April, the Victorian Branch hosted three short talks on Reproducibility and Open
Science, attended by about 40 people.

The evening began with a talk by Hannah Fraser (University of Melbourne) who presented the findings from a survey of 800 ecologists on questionable research practices. About 40% of those surveyed stated that they did add data after analysis, 28% excluded data after analysis, and 64% study more variables than what is reported (i.e. cherry picking of results). Future research Hannah is conducting involves recruiting scientists to analyse two ecology datasets to evaluate how robust the results are to different analysis techniques.

Our second speaker was Fiona Fidler (University of Melbourne) who began with some sobering statistics on the replication crisis; across many research areas less than 50% of results are reproducible. For the psychological sciences, one in a thousand published papers are replication studies, the average statistical power of published studies is <50% and 92% of published studies have statistically significant results. For a solution to this problem, Fiona described the new approach to peer review which has now been adopted by 187 journals. Here at the design stage of a study there is a peer review by a journal of the research questions, study design and planned analysis. And if the study follows very closely the registered report that was peer reviewed than the journal has the obligation to publish the research findings when the study is complete.

Our final speaker was Mathew Ling (Deakin University), who spoke about how individuals still engage in poor behaviours (e.g. people still smoke, scientists still present 3D pie charts). He discussed how we can’t expect researchers to simply change behaviour and practice open science. Instead we need to do more PR activities to promote people doing Open Science and come up with more incentives for researchers to embrace Open Science (e.g. funding bodies).

There was a lively discussion at the end of all 3 excellent presentations. Fiona and Hannah promoted their new crowdsourcing project titled the repliCATS project.

Julie Simpson

South Australia Branch Meeting, April 2019

The speaker for the April 2019 meeting of the SA Branch was Professor Michael Sorich. He is a clinical epidemiologist, biostatistician, and pharmacist from Flinders University with a primary research interest in the use of biological, chemical, and clinical markers to guide decisions regarding the most appropriate use of medicines (precision medicine). His current research primarily focuses on evaluation and evidence development with respect to precision medicine approaches informing the use of cancer medicines. This includes analysis of pooled clinical trial data, and evaluation of patient data from routine clinical care.

Michael’s talk “Efficient development of clinical-grade prediction models of cancer treatment outcomes” is a piece of his current research works funded by a Beat Cancer project grant. At the beginning of his talk, Michael described the precision medicine - an approach to improving the practice of medicine based on understanding the individual characteristics that are associated with, and potentially causative of, drug therapeutic and adverse effects. Using a number of example studies, Michael highlighted the significant advances achieved in precision medicine over the last decade that enable understanding of biological differences between individuals. There are many potential benefits of precision medicine including minimizing risk of drug toxicity, increasing benefit from drugs used, contributing to the sustainability of the healthcare system and facilitating drug discovery and development programs. In particular, Michael highlighted the treatment benefit in advanced cancer by showing a classical example of anti-EGFR therapy for advanced colorectal cancer.

Clinical prediction models were mainly discussed in his talk - an option for providing more personalised estimates of prognosis, harms and potentially treatment benefit. Michael’s talk mainly covered the barriers that exist to developing prediction models that may be used to guide clinical practice and decisions, and emerging data platforms that may help overcome many of these issues. The detail of his talk and particularly prediction models of cancer treatment outcomes can be found by contacting Michael.sorich@flinders.edu.au.

A dinner was held right after the meeting at Jasmin Indian Restaurant, 31 Hindmarsh Square, Adelaide.

By Shahid Ullah

Last week, we heard announcements from the major parties around the environment, equity in STEM and defence. Below we have included relevant links for new announcements and added them to our running tally on our website (accessible by logging on to our members' section). You'll also find key stories and interviews to provide some broader context for how science is being framed in each of the parties' campaigns. Please also help us spread the word about science, technology and their role in Australia's future - a short clip on science and art conservation is our latest feature (Twitter, Facebook, LinkedIn). A new case study will be released each week, shared online using #SolveitwithScience.  Please find a range of relevant links below, and be in touch if we can support your work to get science on the agenda during the Federal Election.

Kind regards,

Kylie Walker CEO Science and Technology Australia

LOG ON TO THE STA WEBSITE

Current Election Commitments: Coalition $30m for the Tasmanian Defence Innovation and Design Precinct $3.7m to improve the health of the SA Torrens River A multidisciplinary hub for sports research will be established in Melbourne worth $15m $960,000 for intensive research into new 4D diagnostic technology Labor  $10m to boost CSIRO Climate Science Creation of Australia’s first National Evaluation Framework for Girls and Women in STEM initiatives, establish a National Women in Science Day, and fund SAGE A 5-point plan to improve the NBN Information resources: The Definitive Candidate list (accurate as of 25/04) Antony Green’s Swing Calculator Antony Green’s Election Coverage AEC election Timetable The Tally Room Key Stories and Interviews: Scott Morison’s Election Campaign Launch Bill Shorten’s Election Campaign Launch Michael McCormack’s Election Campaign Launch Richard Di Natale’s Election Campaign Launch The SBS has published a comparison of education policy The ABC has published a comparison of Climate Change Policy The first leaders' debate will be held in Perth and broadcast tonight on Channel 7Two at 7pm AEST (a second debate is scheduled to be held by Sky News) Latest Polls: Newspoll: 29th April. Coalition-49, ALP-51 (updated) Galaxy Poll: 27th April. Coalition-48, ALP-52 (updated) Roy Morgan: 24th April. Coalition-49, ALP-51 (updated) Essential: 9th April. Coalition-48, ALP-52 Fairfax Ipsos: 7th April. Coalition-47, ALP-53 STA Resources for members A breakdown of current and past STEM policy from the major parties

Science & Technology Australia is offering six scholarships to the 20th anniversary Science meets Parliament this year, to be held in Canberra on 13-14 August 2019.

Science meets Parliament brings around 200 Australian scientists and technologists to Canberra for professional development, networking, and to meet face-to-face with MPs and Senators. It is a highlight of the annual parliamentary calendar and has enhanced mutual understanding between parliamentarians and scientists as well as fostering enduring partnerships and collaborations.

Two (2) Scholarships are open to STEM practitioners in each of the following categories:

• Indigenous STEM Scholarships for people with Aboriginal or Torres Strait Islander heritage
• STEM Pride scholarships for people who identify as LGBTQI+
• Regional STEM scholarships for STEM practitioners who work in remote or regional Australia (>150km from a major capital city)

Scholarships will cover full registration including the gala dinner in the Great Hall at Parliament House, as well as travel, accommodation, meals and transfers. Financial assistance for childcare is available upon application.

Please note that to be eligible for these scholarships you must be a member of or employed by an STA member organisation (such as SSA).

The Indigenous STEM Scholarships are proudly supported by the Australian Academy of Science (AAS) and the ARC Centre of Excellence for Engineered Quantum Systems (EQUS).

Applications will close on 15 June 2019, with recipients to be contacted by 30 June 2019 and an announcement made shortly after.

For more information, or to apply, head to https://scienceandtechnologyaustralia.org.au/scholarships-science-meets-parliament-2019/

It is with great sadness that we communicate the death of Associate Professor Jeff Wood who passed away last month from Motor Neuron Disease. Jeff was a member of SSA since 1974, a former SSA Canberra president, Honorary Treasurer from 1989 - 1992, Circulation Manager for the Journal from 1995 – 1998, and a regular and enthusiastic meeting attendee.

His contributions to the wider statistical community in Canberra and nationally were substantial to say the least. They were recognised with a Service Award in 1999.

Jeff will be sorely missed. He remained active right up until his death, assisting many post-graduate students with statistical analyses as a Visiting Fellow at the ANU Fenner School of Environment and Society. Apart from his research contributions, Jeff will be remembered as one of life’s true gentlemen who graced us with his kindness and humour.

A private funeral will be held in the near future.

Dr Ingrid Aulike, a University of Queensland statistician, won the “Women in Big Data” data challenge for 2019. Her presentation was a masterclass in exploratory data analysis and the importance of not making assumptions about data. Participants were given a dataset with a series of numbers with no apparent meaning. By challenging typical assumptions about data e.g. columns are variables or features, and using different visualisation techniques to summarize the data, Dr Aulike uncovered the hidden figure in this dataset of numbers, an image with a message, “Data Should Be Seen”. In her interview, Dr Aulike highlighted the need for statisticians with strong technical background and consultancy skills to meet the challenges in Big Data. She  credits online courses such as Statistical Learning with Hastie and Tibshirani, Andrew Ng’s Deep Learning and Bill Howe’s Data Science at Scale courses on Coursera as professional development opportunities for statisticians to upskill to address the needs and challenges of Big Data. Congratulations to Dr Aulike!

   

Jeeva Kanesarajah, PhD Candidate
SSA-QLD Newsletter correspondent
The University of Queensland, School of Public Health
raven17786@gmail.com

   

WA Branch April meeting

The April meeting of the Western Australian Branch heard Professor Inge Koch present a talk Analysis of Proteomics Imaging Mass Spectrometry Data. It was a particularly significant meeting as it also celebrated Inge taking up the role of Professor of Statistics and Data Science at the University of Western Australia.

Mass spectrometry measures the weights of charged particles. In this case the particles are fragments of protein molecules from tissue samples and the masses provide signatures for particular proteins. The imaging aspect of the problem is that measurements in the form of mass spectra are recorded over a regular grid of points (or pixels) across the tissue sample. The resulting data is complex, with the spatial aspect of the image overlaid with the need to statistically understand the mass spectra. Effectively each spectrum is a high dimensional vector, typically around 13,000 to 15,000 values so the whole dataset can be thought of as a three dimensional array of data points, with two spatial dimensions and one mass dimension

Inge’s work has come out of a successful collaboration in Adelaide with several biochemists, particularly Lyron Winderbaum and Peter Homann. The aim is to develop methods of identifying features such as cancerous or pre-cancerous cells in a tissue sample without the high cost of an experienced pathologist examining a stained tissue sample under a microscope (the left image below), a process that can take hours.

Inge described several approaches, including images corresponding to the spectra at a single mass (termed feature maps), through to conventional multivariate methods such as principal components, clustering techniques and mixture models. However the feature maps based on a single mass tended to be poor at identifying features in the tissue while the multivariate methods tended to also produce poor images.

The solution was to convert the mass spectra to binary data (presence or absence at each mass), applying a spatial smoothing to the mass data and replacing the Euclidian norm (L2) with the cosine distance. The last is a technique perhaps better known amongst data scientists rather than mainstream statisticians, but its use is growing with high dimensional data. The results are promising in identifying different tissue types as in the central image below.

A final step has been to incorporate knowledge of what actually are cancerous cells to train the methods and select variables (masses) that best distinguish between cancerous and non-cancerous cells. The principle is to find masses that occur predominantly in cancer spectra but not outside, by looking at differences in proportions (DIPPS). The right image below shows the effectiveness of this.

The stained tissue sample with cancerous areas marked (left), the results of cluster analysis (centre) and the prediction from masses chosen by the DIPPS principle (right).

After the meeting a number of members joined Inge for an enjoyable meal at a local restaurant, where the null hypothesis that statisticians are boring and unsociable was firmly rejected.

John Henstridge 

South Australian Branch SSA Meeting: March 2019

The speaker for the March meeting of the SA Branch was Claire Clarke, a methodolgist at the Australian Bureau of Statistics (ABS). Claire gave an engaging talk on the methods being developed at the ABS to improve coordination of samples selected for its household and business surveys.

The ABS conducts a wide variety of sample surveys on social and economic topics. Since different ABS surveys often sample from the same population, sample selection needs to be coordinated in order to manage the survey load placed on individual households and businesses. Also, sample coordination does not always seek to minimise overlap: for surveys which produce estimates every month or every quarter, it is desirable to have high overlap between the samples selected in successive periods. Under the design-based sampling framework used for ABS surveys, a requirement of the sample coordination method is that it preserves each unit’s selection probability specified in the sample design.

For many years the ABS has applied the ‘synchronised selection’ method to achieve sample coordination of its business surveys. Claire explained the method is not particularly flexible, and so the goals of sample coordination are not achieved when units change strata or there are extensive changes to the structure of the sampling frame.

The general ‘Conditional Selection’ method which the ABS has been developing largely addresses the limitations of synchronised selection. Under Conditional Selection, units belonging to the same sampling stratum are selected with different probabilities according to their history of selection across previous surveys. For example, assuming it is desirable to minimise the extent of overlap between the sample for an upcoming survey and the samples of previous surveys, for the upcoming survey the units in the population which have not been previously selected will have highest conditional probability. Claire used an example to explain the calculation of the conditional probability. She illustrated how the probability associated with each potential selection history can be used to ensure each unit is selected with the desired unconditional probability.

In the second half of her talk Claire discussed practical issues for implementation. One such issue is controlling the sample size within each stratum. If it is necessary to control the sample size in each stratum, the selection method needs to be adapted and it is not possible to precisely preserve the desired unconditional probabilities. Another issue is managing the selection history data. Although the selection history (and associated probability the history) must be tracked for every unit in the population, the storage requirements are manageable because the number of possible histories for each unit increases linearly with the number of prior surveys being tracked.

The ABS is in the process of adopting the Conditional Selection method, and it has already been applied for selection for some ABS household surveys.

By Julian Whiting