Menu
Log in


SSA WA: Early Career & Student Statisticians Evening

  • 14 May 2024
  • 5:30 PM - 7:00 PM
  • Cheryl Praeger Lecture Room, The University of Western Australia

Registration


Registration is closed

The WA Branch of the Statistical Society of Australia is delighted to host an evening dedicated to Early Career and Student Statisticians. All visitors are welcome to attend this event, especially anyone studying or interested in pursuing a career in statistics or data science.

Date: Tuesday, 14 May 2024
Time: 5:30PM - 7:00PM
Location: Cheryl Praeger Lecture Room, The University of Western Australia
Cost: Free. Drinks and pizza sponsored by the Branch.

Two speakers have been invited to speak at this event: George Malone (recipient of the 2023 Honours Scholarship) and Alistair Martin (Graduate student at Murdoch).

Presentations

Epigenetic Clocks with Sequencing Data


George Malone, Curtin University

Epigenetic clocks estimate the biological age of organisms based on their DNA methylation levels. Most epigenetic clocks to date are elastic net regression models using DNA methylation array data, such as the Illumina 450K or EPIC arrays. Another method for measuring methylation is sequencing, which measures the same phenomenon and produces similar data. Sequencing is becoming more affordable and popular, and is critical for targeting novel regions of the epigenome. Given the similarities between array and sequencing, can sequencing data be substituted for array in array-based epigenetic clocks? If the data are dissimilar, how sensitive are epigenetic clocks to differences in methylation data?

About the Presenter

After completing a Bachelor of Mathematics and Statistics and working in research for three years, George has now returned to study an Honours at Curtin University. With experience in R and other programming languages, his work to date has mainly focused on statistics and data science in medical research, especially genomic and epigenomic analysis. His interests are varied, but tend towards computing and statistics of biological phenomena, especially in conservation and agricultural contexts.

Optimal Parameter Estimation in the Presence of Contamination


Alistair Martin, Murdoch University

Much of classical statistics is focused on parametric methods, where a model distribution is assumed and it's parameters are estimated from observed data. These approaches are more powerful than non-parametric methods, and we gain information about the structure of the data. However in practice, the true population distribution is unknown and real data rarely conform precisely to our assumptions. It may be that there is a mixture of distributions from more than one population, or simply gross errors. In some cases, a single errant observation has enough influence to invalidate a model. While many procedures exist for manual treatment of outliers, it can be an arduous task. Can we automate this and make our lives easier in 2024?

Robust estimation promises to solve all our woes. Well, some of them; we can have estimators with high efficiency, while assigning zero weight to probable outliers. There are trade-offs, of course, not least of which being that one may first exhaust themselves reading about the plethora of psi-functions and robustness measures available before ever getting to work. This talk aims to help you skip past the fatigue (and the contamination).

About the Presenter

Alistair is a part-time Research Masters with Training (RMT) student at Murdoch university, with a BSc majoring in Mathematics & Statistics and Computer Science. The training component of Alistair's RMT has focused on linear models, robustness theory, and optimisation for deep learning. This has led to research in the field of robustness theory, bivariate M-Estimators, and robust penalised regression under the supervision of Dr Brenton Clarke. During the day Alistair works as a software engineer for Micromine where he mostly writes code in C++, and occasionally gets to dabble in statistics, ML, optimisation, and computational geometry.

Refreshments and Dinner

Members, visitors, and guests are invited to mingle over wine, beer, cider, soft drinks and pizza from 5:30PM. Following the meeting you are invited to dine with fellow attendees at a nearby restaurant. Early career and students will receive $20 off their meal.

Meeting directions

The Cheryl Praeger Lecture Room is located on the ground floor of the Mathematics building at The University of Western Australia. Its entrance is on the northern side of the building. See: UWA Maps, Google Maps.

Parking is free on the UWA Crawley campus after 5:00PM. A convenient place to park is Car Park 18 accessible from Fairway Entry 1.

Registration

This event is free of charge but for catering purposes, please register on this page.

For further information or dietary requests please contact the WA Branch Secretary (ssa.wa.secretary@gmail.com).

Powered by Wild Apricot Membership Software