Join the
Queensland Branch of the Statistical Society of Australia for an engaging Branch Seminar Series, featuring presentations from Queensland-based statisticians through a mix of hybrid and online seminars. In the first webinar of the series, we will showcase the innovative research presented by Queensland travel grant recipients at the 2025 Australian Statistical Conference (ASC2025). This session offers an opportunity to hear from four early career researchers about their statistical research, conference presentation, and their experience attending ASC2025.
Date: Wednesday 22 July 2026
Time: 5:00 - 6:00 pm (AEST)
Format: Online, details will be provided upon registration.
Presenter Bios:
Danyang Dai (Daidai)
Danyang Dai (Daidai) is an applied statistician and infectious disease epidemiologist, finishing her PhD at the University of Queensland, whose research leverages advanced statistical methods and large-scale health data to generate policy-relevant insights in population health. In this presentation, she introduces metaextractoR, an open-source R package designed to streamline data extraction in systematic reviews and meta-analyses—traditionally a labor-intensive and error-prone process—by integrating open-source Large Language Models through the Ollama framework. The tool enables automated, structured, and reproducible workflows via modular Shiny applications, supporting a human-in-the-loop approach where researchers collaborate iteratively with LLMs and perform parallel double extraction in line with Cochrane guidelines. Running fully locally without external data transfer, metaextractoR prioritises privacy, transparency, and reproducibility through comprehensive logging, ultimately lowering technical barriers and empowering more efficient, reliable evidence synthesis.
Nahida Afroz
Nahida Afroz is a health data scientist, statistician, and population health researcher who recently completed her PhD in Mathematical Sciences at the University of Southern Queensland. Her research leverages advanced statistical modelling and large-scale longitudinal health datasets to generate policy-relevant insights into mental health, behavioural risk factors, health inequalities, and health service utilisation among children and adolescents. Her work has involved the analysis of major Australian cohort datasets including the Longitudinal Study of Australian Children (LSAC), the Longitudinal Study of Indigenous Children (LSIC), and Young Minds Matter (YMM), using advanced quantitative approaches such as structural equation modelling, latent class analysis, multilevel modelling, and longitudinal data analysis. In her research, Nahida combines methodological expertise in R, Stata, SPSS, and Python with applied public health research to support evidence-based decision-making and health policy development. She has published in leading international journals including Social Science & Medicine, Journal of Affective Disorders, Applied Psychology: Health and Well-Being, and PLOS ONE, with ongoing research focusing on mental health epidemiology, Indigenous health, and longitudinal population health research.
Prabhashrini Dhanushika Manage
Prabhashrini Dhanushika Manage is a PhD Candidate and Sessional Academic in the School of Computer Science at Queensland University of Technology (QUT). She is passionate about statistics and its role in building reliable, explainable, and trustworthy artificial intelligence. With a background in statistics, her research journey has gradually moved towards artificial intelligence, natural language processing, and transformer-based medical text classification. Her doctoral research focuses on uncertainty-aware machine learning, particularly addressing the reliability of transformer-based classifiers in high-stakes domains such as healthcare. Her ASC2025 presentation topic is “From Black-Box to Transparent AI: A Statistical Framework for Managing Uncertainty in Medical Text Classification”, which presents a statistically grounded framework for managing uncertainty and improving the reliability of AI models in medical text classification.
Lijalem M. Tesfaw
Lijalem M. Tesfaw, is a PhD candidate at the School of Public Health, The University of Queensland. He holds a BSc in Statistics from Bahir Dar University (Ethiopia), MSc in Biostatistics from Hasselt University (Belgium), and an MSc in Industrial Statistics from Bahir Dar University (Ethiopia). His research interests lie in spatial epidemiology, biostatistics, and environmental exposures, with a focus on kidney disease outcomes. He will present part of his PhD research titled “Mapping Kidney Failure Incidence in Australia: Statistical Spatial Analysis Approaches and Their Applications”. This study focuses on the geographic patterns of kidney failure incidence in Australia using various statistical approaches to improve understanding of how kidney failure is distributed across areas and how environmental and geographic factors contribute to this pattern.
@StatSocAus
