top of page
>  2019 APBG Webinar Series
>  2015. Casual Inference in Randomised Trails
Dr. Richard Emsley - Monday 7 Dec 2015


>  2015. RWE Workshop

APBG RWE Workshop Talk 1 - Alan Brnabic


APBG RWE Workshop Talk 2 - David Grainger


APBG RWE Workshop Talk 3 - Laurent Billot


APBG RWE Workshop Talk 4 - John McNeil


>  2014. APBG Mid Year Meeting 2014 Shelia Bird talk


>  2013. APBG 2013_AGM _IanM_talk.pdf


> VicBiostat: Why we need hazards (and why their ratios may display causal intention-to-treat effects)

25th May 2023 4.00pm to 5.00pm AEST


Survival or time-to-event analysis is a key discipline in biostatistics, e.g., put to prominent use in trials on treatment of and vaccination against COVID-19. A defining characteristic is that participants have varying follow-up times and outcome status is not known for all individuals. This phenomenon is known as censoring. If time-to-event and time-to-censoring are entirely unrelated, it is rather easy to see that hazards remain identifiable from censored data, and hazard estimators may subsequently be transformed to recover probability statements. However, COVID-19 treatment (because of competing risks) and vaccination trials (because of event-driven censoring) are just two of the many examples where event and censoring times are related.

For further details and to register for this event, please visit the event page on VicBiostat's website

> VicBiostat: The Rise of the Machines: multiple imputation and machine learning

11th May 2023 09:30am to 10:30am AEST

Royal Children's Hospital, Parkville and Online

Multiple imputation is an important technique for reducing the bias caused by missing data, but it only works if it is used. Automated predictive modelling techniques from machine learning are a promising way to support semi-automated multiple imputation of large data sets. I will talk about two areas of research. First, using ensembles of trees for prediction gives imputation approaches that are competitive with standard methods in quality and scale better with increasing data size. Second, neural networks, which can make up convincing images and text, have the potential to create high-quality imputations. They are not yet ready for use by non-specialists. One of the difficulties in using machine learning for multiple imputation is that the goals of traditional prediction imply different bias/variance/parsimony tradeoffs from the goals of imputation. This is joint work with Yongshi Deng and Keiran Shao.

For further details and to register for this event, please visit the event page on VicBiostat's website

>  2022 APBG Statistics and Data Scholarship Scholarship: Can Statisticians and Data Scientists work together to solve important medical questions? 

7 April 2022 4-5pm Eastern Australia Time - Sydney


Biostatisticians and data scientists often have different approaches to answering important clinical questions.  Classical statistical regression methods used for prediction modelling are well understood in the statistical sciences and the scientific community that employs them. These methods tend to be transparent and are usually hypothesis driven but can overlook complex associations with limited flexibility when a high number of variables are investigated. In addition, when using classic regression modelling, choosing the ‘right’ model is not straightforward. Non-traditional machine learning algorithms, and machine learning approaches, may overcome some of the limitations of classical regression models in this new era of big data, but are not a complete solution as they must be considered in the context of the limitations of data used in the analysis.

The Project

In this presentation our APBG Statistics and Data Science Collaboration scholarship winners Bob Xia (Statistician) and Sarthak Das (Data Scientist) present their research and findings. Bob and Sarthak worked together on a large simulated dataset provided by the APBG to find an algorithm that best fits the data. They explored the different approaches biostatisticians and data scientists have of answering important clinical questions.

>  2021 APBG Webinar Series: The Added Value of Data Science in Pharma: A Data Scientist’s Perspective 

15 July 2021 4-5pm Eastern Australia Time - Sydney


Although not new, Data Science is growing in popularity and many different applications are reported throughout the pharma industry. The aim of this talk is to provide my perspective, as a data scientist, of what data science is, some of the different methods and tools available to a data scientist and the alignment with statistics.  Many of the data science tool are indeed statistical in nature, so what does data science bring to the table? How can statisticians most effectively work with and learn from data scientists and vice a versa? I hope to outline, through the use of examples, a data science approach to a problem with the aim of encouraging statisticians to engage with data science (and even dabble in some of the approaches) so the two communities can communicate, work and learn effectively with and from one another.

Speaker Bio

Jennifer Bradford is Director of Data Science for PHASTAR leading and driving the delivery of innovative data science solutions. Prior to joining PHASTAR she worked in various data science and informatics roles across academia and large pharma. Jennifer earned a Master’s and PhD in Bioinformatics from the University of Leeds University UK and a degree in Biomedical Sciences from the University of Keele, UK.

>  2020 APBG Webinar Series: Variance reduction using CUPED

01 Nov 2020 10am-11am  Eastern Australia Time - Sydney

Variance reduction using CUPED

CUPED is a variance reduction technique published by Microsoft which utilises data from the pre-experiment period to reduce metric variance. It is a post-experiment analysis technique that could increase the statistical power of a test. This talk gives an overview of how CUPED works, and provides some examples of how you may use it in your research. 

Speaker Bio

Derek Ho is an ASTAT accredited statistician working as a principal data scientist at Atlassian. He has a diverse set of experience having worked in marketing, telecommunication and software companies. In his current role, he advises product teams on experimental design, experiment analysis and helps implement statistical methods onto Atlassian’s online experimentation platform.

>  2020 APBG Webinar Series:Bias Control in Observational Studies

15 July 2020 10am-11am  Eastern Australia Time - Sydney

Bias Control in Observational Studies

Observational studies are often thought of as simple studies to design, analyse and report. This myth is busted when I talk about the approaches to comparing treatment outcomes for patients from non-randomised designs. The talk will introduce basic concepts of bias and methods to control for this in observational studies. 

Speaker Bio

Alan is currently Principal Research Scientist at Eli Lilly working in Real World Analytics (RWA) with a focus on specialized analysis that supports this RWE. Prior to this he was the Asia Pacific Director of the Health Outcomes and Health Economics, Life Sciences for OPTUM. Whilst at Eli Lilly he has been the Health Outcomes and Statistics Asia Pacific statistical sciences group leader and manager. He has worked for SPSS Australasia as a Technical Support and Training Consultant; at Macquarie University Practical Demonstrator/Tutor in statistics. He also worked as a Consultant Biostatistician for 5 years in Public Health NSW Health Department. Following that he was a Senior Biostatistician at the George Institute which is affiliated with UNSW where he worked on epidemiological studies and RCTs. Before joining Eli Lilly in 2002 he also took a position at the NSW Department of Corrective Services as Deputy Director of the Research & Statistics, Sydney.

Alan has worked in observational research for 25 years and his interests include the design and analysis of observational studies with a focus on methodologies related to subgroup identification as well as selection bias adjustment tools including matching, propensity score analysis and model averaging. He is also interested in Health Outcomes and statistical approaches used to help support the reimbursement of medicines including NMA.

He has A-STAT Professional Accreditation with the Statistical Society of Australia (SSA). He is an active member and Chair of the Australian Pharmaceutical Biostatistics Group (APBG)

>  2020 APBG Webinar Series:Cluster Randomised Trials

Tue 4 Feb 2020 9am – 10am Eastern Australia Time - Sydney

Speaker Bio

Jessica Kasza is a senior lecturer in the Biostatistics Unit located in the School of Public Health and Preventive Medicine at Monash University. After completing a PhD in 2010 at the University of Adelaide, she spent time at the University of Copenhagen, before returning to the University of Adelaide. She has been at Monash University since 2013. She leads the development of statistical methodology for longitudinal cluster randomised trials, including the stepped wedge and cluster cross over designs, and has interests in the comparison of healthcare providers and causal inference. Jessica is the Vice President of the Statistical Society of Australia. You can find out more about her research at

>  2019 APBG Annual General Meeting

Mon 9 Dec 2019 2:30pm – 5pm :George Institute, Level 5, 1 King St, Newtown

Talk: Early stopping of clinical trials: impacts on treatment effects, meta-analyses and cost-effectiveness

Ian Marschner is Professor of Biostatistics at The University of Sydney, in the NHMRC Clinical Trials Centre

14 May 2019: Practical applications and lessons learnt from case studies of biomarker analysis in drug development

William Reece, Statistical Fellow & Director, Commercial Support Services, Covance

25 July 2019: Generalizing from RCTs to real world populations

Mark Belger , Principal Research Scientist, Eli Lilly

September 2019: Upcoming: Joint Webinar with PSI

>  2016 Mid Year Seminar - Quasi-Experimental designs

Stepped-Wedge Trials - Serigne Lo 2016

Interrupted Time Series - Timothy Dobbins 2016

Quasi Experimental Designs - Ines Krass 2016

>  APBG Constitution.doc (34K)


>  2013. APBG Constitution 25 Feb 2013.pdf


>  2013. Mid Year Meeting 2013.pdf


Biomarker choice.pdf


FDA Missing Data2.pdf


Heritier_JM_SAFE_TBI_v03_July_2013.pdf (1.1M)



>  2012.  MID Year Meeting


Log-binomial regression - Sydney APBG 2012 (Laurent Billot) v4.pdf (737K)


Missing Data in Clinical Trials Trial APBG 22 Aug 2012.pdf (296K)


Hot topics in stats 22AUG2012v2.pdf

>  2011. MartinBlandReportingclinicaltrialswithconfidence.pdf (53K)
>  2010.  APBG AGM


APBG_AGM_Dec2010_final.pdf (1.1M)


>  2008.  Monthly Notice - ST_July08.pdf
>  2008.  Integrating Statistical Ideas into mathematics 2 Workshop 6 Aug 08.pdf (40K)
>  2008.  Monthly Notice - 2008 Oct.pdf)


>  2007.  Indirect Comparison


ICHAWorkshopMar2007.pdf (54K)


Stats Indirect Workshop (b) Kris and Bill.pdf








Annie Solterbeck v2.pdf


APBG Session 4.pdf

bottom of page