STATS MATTERS & EVENTS

29 October 2020

Dear {Contact_First_Name},

I am so delighted for our members in Melbourne as lockdown rules were officially eased just a little while ago. As the weekend is approaching, I’ll be thinking of you, as you get to have your first meal in a restaurant again, your first drink at the pub, your first haircut or your first bike ride in months! Let’s hope we continue to keep COVID-19 in check within Australia, giving us some semblance of a normal life, while things look worrying in many other countries.

This newsletter tells stories of past events and highlights a few new ones. Enjoy!

Kind regards

Marie-Louise Rankin
SSA Executive Officer

Read newsletter in your browser

NSW Branch Hosts Its First Ever Pandemic Lancaster Lecture (October 2020)

Branch President Thomas a presents his count response methodology to a large inter-state audience using Zoom. 

The 2020 pandemic situation meant that, for the first time, the New South Wales branch's annual Henry Oliver Lancaster lecture could not be delivered live in a Sydney lecture room with auxiliary drinks and food. Instead we had a large Zoom hook-up - which at least meant that those from other parts of Australia were able to listen to current branch president, Thomas Fung, describe his recent count response methodology research. Thomas' talk was titled "Count on someone who can count!".

First Thomas summarised some of the work of Professor Lancaster, including his "Bibliography of Statistical Bibliographies". After that we moved into his recent methodology and R package concerned with generalised linear models for count response data. The first family of response distributions, known as the Conway-Maxwell-Poisson family, extends the Poisson distribution with an extra parameter that facilitates both over-dispersion and under-dispersion.
Thomas told us how his co-author, Alan Huang, has developed an interesting parameterisation in terms of the mean response. Users of R can try out generalised linear models with this family using the package "mpcmp", which is authored by Thomas, Alan, Aya Alwan and Justin Wishart.

Some of the pros of the mean-parameterised Conway-Maxwell-Poisson model for count data include it being comparable with commonly used log-linear models and easy offset incorporation. Some compelling illustrations were given of this new generalized linear model from our part of the world.

The last phase of the 2020 Lancaster Lecture got into zero-inflated models for count data. Thomas explained how their new approach to parametrisation leads to interpretation gains and overcomes the need to specify an explicit model for the zero-inflation process.

Unlike previous year's lectures, we were not able to walk up to a restaurant in Newtown. We still plan to toast Thomas' excellent Lancaster  Lecture at a future social gathering.

Matt Wand
University of Technology Sydney

SSA SA Branch September Meeting

Propensity score techniques in multiple treatments framework: the estimation of neighbourhood effect

The speaker for the September branch meeting was Margherita Silan, who is a postdoctoral research fellow at Padua University and who presented via Zoom from Italy. Margherita was the winner of the Italian Statistical Society annual award for best PhD in Applied statistics. Her research interests include causal inference in multiple treatment frameworks, composite indicators and partially ordered set theory with applications in public health, ageing and gender equality. Magherita’s talk covered the estimation of a geographic neighbourhood effect on health outcomes using modified inverse probability of treatment weighting, logistic regression and a novel method called Matching on Poset based Average Rank for Multiple Treatments (MARMoT).

Click here for Lan Kelly's full article

Obituary

Bill Whiten 1942-2020

------------------------------

Sadly, Dr Bill Whiten, who was a long-time member of the SSA Queensland Branch, passed away in September after a two-year battle with Leukemia. He was a retired professor who spent 45 years with the Julius Kruttschnitt Mineral Research Centre at the University of Queensland.

Bill will be fondly remembered and missed by the Queensland Branch. He was a stalwart of the Branch who attended most meetings, even after they moved to Zoom this year. He had wide ranging mathematical and statistical interests and his last presentation to the Queensland Branch was in 2017 when he talked about testing for bugs in Adelaide water, fitting a flood distribution in north Queensland, regularisation of a model with excess parameters, grey box models (his favourite), and comparing non nested models in regression. We send our sincere condolences to his family.

Please see

PhD scholarship opportunity: Sit, sleep, play, repeat? An international database to understand movement behaviours in early childhood – the Sleep and Activity Database for the Early Years (SADEY) 

An exciting 3-year PhD scholarship opportunity is available for candidates living in Australia or New Zealand who are interested in researching the health behaviours of kids during early childhood. The successful candidate will work with leading researchers internationally to support the development of a large international database known as the Sleep and Activity Database for the Early Years (SADEY). We are open to potential candidates from a range of disciplinary backgrounds including physical activity and public health, data science/statistics, informatics/programming or related areas. 

(Funded as part of an Australian Research Council funded Discovery Project - DP200102008).

More information about this opportunity can be found here

The Environmental Statistics Section of SSA is pleased to present the following webinar

Bayesian hierarchical modeling and data fusion for multivariate speciated nitrogen in lakes

with Erin Schliep (University of Missouri)

Friday, 30 October 2020  at 10am  AEDT.

For more details about this talk click here.


Join this webinar

Should statisticians all work from home even after lockdown? Join us for a virtual debate

17 Nov 2020, 5:30 PM – 7:00 PM

The number of people working remotely increased dramatically after the first COVID-19 restrictions were put in place. Should statisticians continue to work from home even after restrictions are eased?

Join us for a fun virtual debate, where we have the pleasure of hosting four speakers, at different stages of their career to give us their opinions on the topic. Debate will involve two teams that will present their arguments on each side of the issue.

Each speaker will give a 10 minute talk followed by a 20 minutes of panel discussion and Q&A from the audience. After the event, we will retire to a social gathering platform, that isn’t Zoom! There we will do some socialising, as well as have an opportunity for audience members to freely approach each other and the speakers.

Speakers

Emily Karahalios
Karen Lamb
Thomas Lumley
Andrew Robinson

Register here

In 2020, AMSI BioInfoSummer is going virtual! Hosted by The Australian National University (ANU), attendees will participate online over the four-day program to develop their bioinformatics skills, national networks and employability.

Join with other advanced undergraduate and postgraduate students, researchers and professionals from the mathematics, statistics, medical sciences and information technology disciplines to explore bioinformatics under the following themes:

  • Single cell / transcriptomics
  • RNA biology
  • Long read sequencing
  • Biomedical optimisation / data science

Featuring presentations, workshops and program extras from the best in the bioinformatics field from Australia and abroad, the AMSI BioInfoSummer 2020 program is jam packed. Start each morning with a mix of computational and biology focused lectures and research talks. Then develop your skills during the hands-on workshops. Round out your week with an interactive careers session, ePoster competition and public lecture.

Full four-day conference registrations start from $60!

Find out more

With a record-breaking 171 attendees in 2019, the annual AMSI Summer School is the biggest national event in Australia for honours and postgraduate students in the mathematical sciences.

In January 2021 this four-week school will be hosted virtually by The University of Adelaide, providing students from across Australia with the opportunity to develop their mathematical skills, meet like-minded people, and network with potential future employers at the Careers Day.

AMSI Summer School 2021 offers eight exciting subjects by specialist lecturers from around Australia and students can study one or two subject areas including one subject for credit.

Honours and postgraduate students in the mathematical sciences and cognate disciplines are invited to register their interest for this event, as well as researchers and professionals who may wish to get involved in the program extras offered at the AMSI Summer School.

To maximise the students’ experience, the School will feature domestic keynote speakers, researchers and/or lecturers, as well as a number of program extras including social events, a special guest public lecture, a careers session, and a Diversity in STEM panel event.

SSA is a proud sponsor of this event.

Interested in finding out more about Summer School 2021?

Join the AMSI Summer School Mailing List

From SMRI Executive Director Anthony Henderson:

Applications are now open again for the Domestic Visitor Program of the University of Sydney Mathematical Research Institute (SMRI). Complementing our flagship International Visitor Program, this scheme is for researchers in the mathematical sciences from other Australian universities who wish to do research at SMRI, either individually or as part of a group of collaborators. Funding is available for successful applicants who are not based in Sydney. 

This application round is for visits of at least 2 weeks within the period 1 March - 26 July 2021. Applications close on Monday 30 November 2020 and should be sent by email to smri.exec@sydney.edu.au with the information requested in the terms and conditions on the SMRI website.  

Applications from female and gender-diverse researchers, and from researchers belonging to other groups which are underrepresented in the mathematical sciences, are particularly encouraged.

Please direct questions about the conditions to the Institute's Executive Director

Anthony Henderson.

 
 
Book here
 

Don't miss ACEMS’ final free public lecture for the year


The lives and deaths of ethical AI
 

with Ellen Broad, 3A Institute, ANU

Wednesday 11 November, 12pm-1pm AEDT

Over the last decade, ideas of ‘ethical’ AI have transitioned from research papers, community projects and side panels to dedicated organisations, funding streams and keynote slots. We’ve moved from ethical principles, to proposed technical interventions, to re-framing of ethical issues as issues of justice, structural oppression and systemic failure. There’s been ethics washing, ethics bashing, and ethics selling. Has ethical AI run its course, or courses? And if ethical AI is dead, what comes afterwards?

In this lecture, Ellen Broad (Senior Fellow, 3A Institute, ANU) explores recent evolutions and transitions in ethical AI, its influences and failures, and looks to what might come next, against the backdrop of a year of profound social, economic and environmental upheaval for us all. 

A list of ACSPRI’s Summer 2021 courses is available now!

The Australian Consortium for Social and Political Research Incorporated (ACSPRI) have decided to offer the Summer 2021 program online using Zoom.  The courses will be held over 3 weeks in January and February 2021.

The early bird discount for Summer 2020 expires on 9th December.

Click here to see what’s available and to book

CPD mentoring sub-committee – MEMBERS WANTED!

Statisticians frequently find themselves in fairly unique work positions, often the only statistician or one of few statisticians working within multidisciplinary teams. This can lead to less experienced statisticians feeling isolated and unaware of how to grow and develop within the profession. One way to support emerging professional statisticians in developing the personal and professional skillset needed to be successful in the workplace is via mentoring.

The Continuous Professional Development committee is seeking new members to help support the development of a SSA mentoring program based on the program piloted by the Biostatistics & Bioinformatics Section in 2020. This program will be launched in 2021 and CPD mentoring sub-committee members are required to help support the expansion of the program, reaching out to other SSA Sections and Branches to build a mentor list and work closely with the Early Career & Student Statisticians Network to link mentors with mentees. We encourage people from all backgrounds, employment sectors and experience levels to reach out and are committed to having a team that is made up of diverse skills, experiences and abilities. We actively encourage those of you who may not have been actively involved in the SSA in the past to reach out to help expand and diversify our SSA community. If you are interested in becoming involved, please send an email including a couple of paragraphs about yourself and why you want to be involved in the program to Karen Lamb at klamb@unimelb.edu.au by November 13th. Please don’t hesitate to reach out if you want any further information.

Are you a Statistician by day and a Renaissance Artist by night?

We need your help in designing our new and official SSA t-shirt. Submit a t-shirt design to the online SSA T-shirt Competition. The winner will receive a $100 gift card and eternal bragging rights! All SSA members are welcome to submit an entry by COB Friday 4th December 2020.  

Click here for more information.

Looking for an Event Coordinator

This is a paid role, 6-8 hours a week, to help the SSA office manage the many online events that are currently being hosted. If you can think of someone who might be interested, please pass on this position description to them.

Webinar Course “Statistical Inference in Markov Processes”

The Latin American Regional Section of the IASC (International Association of Statistical Computing) is pleased to invite postgraduate and undergraduate students to attend the Webinar Course “Statistical Inference in Markov Processes”. The course will be team-taught by Professors Verónica González-López and Jesús E. García from University of Campinas, Brazil.

The course will be held virtually using the platform GoToWebinar from 23-26 November 2020. The deadline for registration has been extended until November 6, 2020. To attend this virtual course, please complete the IASC-LARS Webinar Registration Form and sent it to lacsc.lars.iasc@gmail.com

Find out more

Previously advertised

The Statistical Society of Australia warmly invites you to a workshop on

Data Wrangling with R, taught by Dr. Emi Tanaka

1-2 December 2020, 1:30pm-5:00pm(AEDT).

Data wrangling is one of the first key steps necessary before downstream analysis such as visualization or modelling. This workshop will teach you how to wrangle data in the statistical language R using the tidyverse suite of packages, i.e. dplyr, tidyr, stringr, lubridate and forcats. This will include learning about the concept of tidy data and learning the new verbs in dplyr v1.0.0 released early this year. The workshop will be hands-on with plenty of practical examples and time for participants to work through exercises to put what they learnt into practice.

Find out more and register here

Please join us for the webinar

The Advent of "Grammar": Bridging Statistics and Data Science for the Design of Experiments 

presented by Dr Emi Tanaka

on 27 November 2020, 1pm AEDT via Zoom. 

Statistics is a valuable tool for almost all scientific fields and industry to make sense of their data, yet as a field we lag behind to remain relevant, getting superseded by the so-called data science. What differentiates statistics from data science? And how does the design of experiments fit in with data science? 

In this webinar, Dr Emi Tanaka will talk about the concept of the "grammar" and the momentum it is gaining to make data analysis more accessible to a diverse group. She'll then present her prototype to the "grammar of experimental design" - a framework to construct the design of comparative experiments that cognitively enforces the experimental structure. She’ll explain some principles behind this prototype, showcase how her developmental R-package edibble will work, and how she thinks it helps to bridge the gap between experimental design theory and practice for the wider community.

Register here

The Bayesian Section of the SSA is pleased to announce the following webinar 

Computing Bayes: Bayesian Computation from 1763 to the 21st Century 

with Gael M. Martin on 11 November 2020 at 4:00PM (AEDT).         

About this webinar:

The Bayesian statistical paradigm uses the language of probability to express uncertainty about the phenomena that generate observed data. Probability distributions thus characterize Bayesian inference, with the rules of probability used to transform prior probability distributions for all unknowns - models, parameters, latent variables - into posterior distributions, subsequent to the observation of data. Conducting Bayesian inference requires the evaluation of integrals in which these probability distributions appear. Bayesian computation is all about evaluating such integrals in the typical case where no analytical solution exists. This paper takes the reader on a chronological tour of Bayesian computation over the past two and a half centuries. Beginning with the one-dimensional integral first confronted by Bayes in 1763, through to recent problems in which the unknowns number in the millions, we place all computational problems into a common framework, and describe all computational methods using a common notation. The aim is to help new researchers in particular - and more generally those interested in adopting a Bayesian approach to empirical work - make sense of the plethora of computational techniques that are now on offer; understand when and why different methods are useful; and see the links that do exist, between them all.

To find out more and to register

Statistics in the Capital...Knibbs Lecture: A personal tour with Raymond Carroll

SSA Canberra invites you to attend this year's Knibbs lecture, which will be presented by Prof. Raymond Carroll (Texax A&M). Prof Carroll will provide a personal tour of his experience in developing statistical methods to understand how to measure dietary intakes in a population and how to relate such measures to mortality and chronic diseases. The lecture will also celebrate the 60th birthday of Prof. Alan Welsh (ANU), and his contributions to statistics.  

Date and time: 

Tuesday 24th November; 12:30pm-1:45pm AEDT.  


Learn more and RSVP here


Tired of surveys but eager to leave feedback? Tell us what you are missing from your SSA membership. Or let us know what we do well. We will listen. 


Contact us

Statistical Society of Australia |  PO Box 213 Belconnen ACT 2616 Australia 

02 6251 3647 | www.statsoc.org.au