Dear {Contact_First_Name},
|
TELL US WHAT YOU THINK IN ONE MINUTE! Member surveys can be cliche but it is valuable for a number of reasons; they allow us to collect important feedback, potential to make improvements and a great opportunity to understand our members. The benefits and services are the heart of everything SSA does and we value your voice in shaping the organisation. New to SSA - I am keen to learn more about you and encourage you to share your honest feedback. The survey will take no more than a minute. Help us define and understand what membership looks like to you!
Regards
Vanaja Thomas, General Manager
|
|
|
|
|
|
|
SSA VIC & TAS Presentation by Dr Carolyn Huston
Dr Carolyn Huston, a Principal Research Consultant at CSIRO, gave a lively and stimulating presentation to the Vic & Tas Branch on "Explainable AI and Different Types of Graphs". She pointed out that there was an important gap in the use of so-called "explainable" methods and models: context matters, what counts as an explanation to a statistician or other data scientist is not necessarily what counts as an explanation in the mind of an ordinary user of the model. This was even more important when models are advertised under the label AI. Recognising the importance of making sure that the ideas of statistical inference are given due regard, she emphasised that there is an ethical dimension to the responsibility to provide explainability as explainability also enables models and their interpretations to be contested and their underlying bases to be understood and assessed. She referenced Australia's Artificial Intelligence Ethics Framework as being something all practising data scientists should be aware of and perhaps aspire to. Around the concept in particular of explainability she suggested ideas from the field of Design Thinking could be helpful. She referred to affordances, signifiers and cognitive models as providing a potential framework for developing better explainability of models and methods. She also observed that conceptual models do not have to be complete in order to serve as part of an explanation. With a change of pace and direction, Carolyn gave examples of (vertex-edge) graphs which served as the basis of models in different fields, including electrical energy distribution. She explained, for example, that properties of the graph (such as measures of connectedness) were used by engineers in order to try to understand how to make networks resilient. She said however that simple descriptive statistics clearly were not enough to account for the behaviour of complex networks (and she showed an example from electrical energy distribution). There was more work to be done on the development of useful statistical descriptions, with corresponding measures of uncertainty. After some questions, the meeting adjourned to a nearby restaurant. The meeting was attended on a rather unprepossessing night by 18 people at the Caulfield campus of Monash University, and by 62 people on-line, including those present in person at the Hobart hub. |
|
|
|
|
SSA Annual General Meeting followed by Guest Speaker presentation 27 August 2024 | 5:30pm | Online |
Registration is open! The Annual General Meeting (AGM) of the Statistical Society of Australia will be held online on Tuesday, 27 August at 5:30pm AEST followed guest speaker presentation by Lynne Giles. While all members are invited only financial members are eligible to vote. The quorum for the meeting is 20 voting members attending online or by proxy. All documents for the meeting including agenda and the proxy form will be made available in the following weeks. Program: 5:30PM Welcome 5:35PM AGM Formalities & Announcements 6:00PM Guest Speaker Presentation 6:20PM Q & A 6:30PM Close We hope to see you there! |
|
|
|
|
|
|
SSA Early Career & Student Statistician Conference | 18 - 21 November 2024 |
|
|
|
|
The ECSS Network of SSA and SECS Network of NZSA are excited to announce that abstract submissions and registrations are now open for the Early Career & Student Statisticians Conference (ECSSC). This event provides invaluable insights and networking opportunities for early career and student statisticians. Submission for this conference ends on Friday, 2 August 2024.
This year, we are thrilled to host local hubs in Perth, WA, Hobart, Tasmania, and Christchurch, New Zealand, along with a livestream option. Don't miss out on this incredible experience!
Submit your abstract via Jotform: https://form.jotform.com/240894438147869
Register Now:
-
Register for the Perth Hub
-
Register for the Hobart Hub
-
Register for the Christchurch Hub
-
If you intend on attending online, click any of the hubs to register.
Important Dates:
-
11 July 2024: Call for abstracts
-
11 July 2024: Registrations open
-
2 August 2024: Deadline for abstract submission
Please note that these dates might be adjusted as the conference approaches.
For more details, visit the conference website. |
|
|
|
|
|
|
|
|
This is an ABS double header with presentations from Jason Eridani & Julian Whiting.
Overview of the Intergenerational Health and Mental Health Study-Jason Eridani
The Intergenerational Health and Mental Health Study (IHMHS) is the largest health study undertaken in Australian history, aiming to provide a comprehensive understanding of nation’s physical and mental wellbeing. The IHMHS comprises 4 national surveys: (i) National Study of Mental Health and Wellbeing; (ii) National Health Study; (iii) National Nutrition and Physical Activity Study; and (iv) National Health Measures Study.
This presentation will provide an overview of the IHMHS including outlining the recent National Health Survey and National Study of Mental Health and Wellbeing publications and available microdata products. Upcoming releases for the National Aboriginal and Torres Strait islander Health Survey will be discussed. The presentation will conclude with a detailed overview of the Nutrition and Physical Activity surveys’ collection methods and collaboration with Food Standards Australia New Zealand.
Methods for using new data sources in the Australian CPI-Julian Whiting
The Consumer Price Index (CPI) is Australia’s official measure of household Inflation and is published on a quarterly basis. By late 2025 the Australian Bureau of Statistics (ABS) will release a complete monthly measure of the CPI. The transition to a complete monthly measure has been facilitated by acquiring new data sources which has significantly improved data collection efficiency. These new data sources, such as point-of-sale transaction data and web-scraped data, exist for some other purpose, but compared with manual price collection they provide richer information for CPI compilation. Adopting the new data sources often requires changes to the methods used to aggregate price observations to compile the CPI. The new methods not only seek to maximise the value of the richer data, but also manage features which reflect the original purpose of the data source. This talk will provide an overview of the data collection and compilation of the CPI, and outline some of the methodological issues and challenges for adopting the new data sources.
|
|
|
|
|
|
|
Room 501.117, Curtin University
Openly sharing research data and code for analysis and other scientific software has been frequently discussed as an essential practice in scientific research to allow proper evaluation of the claims. Previous SSA events have highlighted this issue, but to my knowledge none have presented an analysis of the state of reproducibility as found in the literature. As scientific claims can ordinarily only be evaluated by the description of the protocols, materials, equipment and methods described in peer-reviewed articles and as these methods and data become more complex it becomes critical to share what is behind this text in the article. To freely and openly share protocols, data and computational code greatly enhances the impact of the research, yet in many areas of research this practice remains quite limited. To evaluate the state of openness and reproducibility in plant pathology, we selected 450 articles published from 2012 to 2021 across 21 journals from the of field plant pathology randomly and scored them for their openness and computational reproducibility. The scores were then analysed by fitting Bayesian logistic mixed models to evaluate the effects of year of publication, journal title and five-year impact factor on the openness and reproducibility of the articles’ content. Most of the articles examined did not follow protocols for open science and failed to share data or code that other researchers could easily access, use and assess. Additionally, we were unable to detect any effect from year, journal or impact factor on openness and reproducibility. However, examples currently exist in a range of options to draw from that can provide ideas for those that may be unfamiliar with where to start. As biometricians, we are perhaps among the best-equipped researchers to help drive this paradigm shift by making our analyses reproducible, first for ourselves and then by sharing them openly for others to see, use and evaluate making our science more open and reproducible. |
|
|
|
|
|
|
This talk is a follow up to last year’s presentation by Olivia Angelin-Bonnet on the relevance of software engineering best practices in statistics and data science. Here, Olivia will go through how she setup a new data analysis project in R, following some of these best practices to ensure reproducibility and reusability. In particular, she will demonstrate how she use GitHub to version control my code, and how she organise a typical analysis directory. Olivia will also showcase some very useful R packages, such as renv to document my computational environment and targets to turn my scripts into a reproducible analytical pipeline.
|
|
|
|
|
|
|
Room 5040, Level 5, Business School Abercrombie Building, The University of Sydney
We are happy to announce a joint event with Royal Statistical Society's section on Finance and Economics and The University of Sydney Business School with a seminar by Gianni La Cava, Research Director at the e61 Institute.
Gianni La Cava will present: The Effects of Monetary Policy on Consumer Spending: Insights from Australian Bank Transaction Data
We hope to see you there.
|
|
|
|
|
|
|
This is the first in the series of webinars that focus on the personal journey of older Australian statisticians that have made a difference.
What to Expect:
-
Interview Session: Conducted by Dennis Trewin, former SSA President and History Committee member, Brian will reflect on his path from secondary school mathematics teacher to Associate Professor at Swinburne University. His journey is unique, transitioning into Applied Statistics and shaping graduate programs in statistics education.
Why Attend?
Who Should Attend?
Early career statisticians Students aspiring in statistics and related fields Anyone interested in the history and development of statistics education
Registration is free but required to secure your spot.
|
|
|
|
|
|
|
Machine Learning II
23 Sep AEST – 11 Nov 2024 AEDT | Online- 1 hour a week
The Social Research Centre and the Statistical Society of Australia (SSA) are very proud to offer statistical training from the International Program in Survey and Data Science (IPSDS), a joint program of the University of Mannheim and the Joint Program in Survey Methodology at the University of Maryland. There are only a few spots left.
Social scientists and survey researchers are confronted with an increasing number of new data sources such as apps and sensors that often result in (para)data structures that are difficult to handle with traditional modeling methods. At the same time, advances in the field of machine learning (ML) have created an array of flexible methods and tools that can be used to tackle a variety of modeling problems. Against this background, this course discusses advanced ML concepts such as cross validation, class imbalance, Boosting and Stacking as well as key approaches for facilitating model tuning and performing feature selection. In this course we also introduce additional machine learning methods including Support Vector Machines, Extra-Trees and LASSO among others. The course aims to illustrate these concepts, methods and approaches from a social science perspective. Furthermore, the course covers techniques for extracting patterns from unstructured data as well as interpreting and presenting results from machine learning algorithms. Code examples will be provided using the statistical programming language R. |
|
|
|
|
Save the Date 2024 ADSN Conference
We are excited to announce that this year’s ADSN Conference will be in Perth. The host organisation for the conference is the Curtin Institute for Data Science.
This year’s conference will be extended to three days, with the third day being industry-focused. It will also include a visit to the Pawsey Supercomputing Research Centre.
When: Mon-Wed, 2-4 December Where: Curtin University, Bentley Campus
Abstract Submissions and Registrations will open soon! |
|
|
Expand Your Mathematical World
AMSI Summer School is an annual national training and networking event for honours and postgraduate students in the mathematical sciences and related disciplines, early career researchers and industry professionals looking to upskill.
Celebrating its 23rd year, Summer School 2025 will be hosted by The University of Sydney from 6 – 31 January (virtual participation also available).
Connect with peers, researchers and potential future employers while developing your mathematical skills. You can even take a subject for credit!
|
Celebrating its 23rd year, AMSI Summer School is Australia's biggest annual national event for honours and postgraduate students in the mathematical sciences. Connect with peers, researchers and potential future employers while developing your mathematical skills.
Interested in machine learning, financial mathematics, statistics or are you more of a pure maths type? Take a look at our subjects and see what piques your interest.
Choose up to two subjects to study over the four-week program. Students can choose to take one subject for credit towards their degree with the permission of their home university.
|
View subjects--https://ss.amsi.org.au/subjects/ |
|
|
|
|
Unlock your potential at the upcoming Women in STEM Careers and Entrepreneurship Masterclass, hosted by the Australian Mathematical Sciences Institute and Western Sydney University. This exclusive event will take place from 21 - 23 October at the Parramatta City Campus, Western Sydney University.
Designed for women STEM researchers, this masterclass offers a unique opportunity to delve into Australia’s research commercialisation and innovation ecosystem. Gain insights directly from industry and university experts in research innovation, and hear success stories from researchers who have transitioned into leading roles in startups or R&D teams.
Who should attend?
If you are a STEM research student or an early to mid-career researcher, this masterclass is tailored for you. We especially encourage those who have participated in an APR Internship, funded by APR’s WISE program, to take advantage of available sponsorships covering accommodation and travel expenses.
Event Details
Time and Date: 9am - 5pm AEDT, 21 - 23 October 2024. Location: Level 9, Paramatta City Campus, Western Sydney University. Cost: $130 GA, Free for APR.Intern WiSE subsidy recipients.
Join us at the forefront of STEM innovation and entrepreneurship.
We look forward to welcoming you to Sydney this October! |
|
|
|
|
|
|
The International Environmetrics Society (TIES) is a non-profit organization aimed to foster the development and use of statistical and other quantitative methods in the environmental sciences, environmental engineering and environmental monitoring and protection. To this end, the Society promotes the participation of statisticians, mathematicians, scientists and engineers in the solution of environmental problems and emphasizes the need for collaboration and for clear communication between individuals from different disciplines and between researchers and practitioners.
All contributions related to environmetrics are welcome from across academia, research institutes, government, business and industry.
Key Dates:
| Deadline for Invited Paper Sessions |
15th July 2024 |
| Deadline for Contributed Papers |
15th Aug 2024 |
| Invited paper contributors informed of outcome |
31st July 2024 |
| Contributed paper authors informed of outcome |
9th Sept 2024 |
| |
|
| Registration opens |
15th July 2024 |
| Deadline for early registration |
23rd Sept 2024 |
For questions contact: John Boland john.boland@unisa.edu.au
|
|
|
|
|
|
|
JSM 2025 is now open to invited proposal submission
The theme for JSM 2025 is “Statistics, Data Science, and AI Enriching Society,” but not all sessions have to adhere to this theme. Formats vary for invited sessions; however, all are 110 minutes in length and have a session chair. The sessions typically include 2–6 participants, including the chair, with two of the most popular and successful formats being 2–3 speakers with a discussant or a panel discussion of 3–5 panelists.
To get session information into the early planning stages for JSM 2025, all session proposals must be submitted online. The submission site will be open through September 5, 2024 (11:59 p.m. ET).
In order to submit a proposal, organizers will need the following information:
Session Type (Invited Paper or Invited Panel) Sponsor (JSM partner society/ASA section or committee, Memorial, etc.). A pre-approved list is provided; select no more than three. Session Title Session Description (provide a short description, including focus, content, timeliness, appeal, and format) Session organizer, including affiliation and email address Session chair, including affiliation and email address Session speakers and any discussants, including affiliations and email addresses
|
|
|
Logistic Regression 5 Day Masterclass
Deakin Epidemiology is pleased to offer a summer Masterclass focused on Logistic regression to be delivered by arguably the world’s most famous teacher of this statistical technique – Prof. Stanley Lemeshow. In years past, Lemeshow together with Ken Rothman offered back-to-back masterclasses in Biostats and Epi in Tasmania which were a bit of an institution, with many epidemiologists and biostatisticians building their knowledge and networks by heading south for a healthy dose of upskilling or as a refresher. Stan has agreed to offer this program onshore once again in Australia, this time at Deakin University’s Melbourne CBD campus 727 Collins Street, Docklands VIC 3008.
This 5-day course (Feb 24-28, 2025) will provide theoretical and hands-on practical knowledge and skills in statistical modeling with an in-depth focus on logistic regression analysis – the standard method for regression analysis of binary, multinomial and ordinal response data in health research. Each day comprises a 4-hr class in the morning and a 2-hr practical session in the afternoon and opportunities to network with fellow health and medical practitioners and researchers.”
Places are limited, so get in early! |
|
|
|
|
|
|
|
|
|
|
The SSA team would love to hear from you! If you have any feedback or news from the Australian statistical community to share in Stats Matters and Events, please get in touch with us!
|
|
|
|
|
|
