20-21 October 2022,  2-Day workshop:

Estimands, Estimators and Estimates: Aligning target of estimation, method of estimation, and sensitivity analysis  

Presented by Dr Frank Bretz at the Macquarie University Sydney City Campus

Register now at: https://www.statsoc.org.au/event-4975583 

Description: The ICH E9(R1) Addendum on 'Estimands and Sensitivity Analysis in Clinical Trials' introduced a framework to align planning, design, conduct, analysis, and interpretation of clinical trials. When defining the clinical question of interest, clarity is needed about 'intercurrent events' that affect either the interpretation or the existence of the measurements associated with the clinical question of interest, such as discontinuation of assigned treatment, use of an additional or alternative treatment and terminal events such as death. The description of an estimand should reflect the clinical question of interest in respect of these intercurrent events, and the Addendum introduces strategies to reflect different questions of interest that might be posed. 

This two-day course will introduce the estimand framework according to the ICH E9(R1) Addendum. Using a generic example to illustrate the thinking process that aligns estimands and sensitivity analyses with trial objectives, we will provide an in-depth description of intercurrent events and various strategies for addressing them when defining the clinical question of interest. The choice of strategies can influence how more conventional attributes of a trial are reflected when describing the clinical question, for example the treatments, population or the variable (endpoint) of interest. For a given estimand, an aligned method of analysis, or estimator, should be implemented that is able to provide an estimate on which reliable interpretation can be based and which includes the handling of intercurrent events, missing data and sensitivity analyses. We will therefore also discuss how to identify and implement analyses approaches as well as sensitivity analyses that are aligned with a chosen estimand for different types of endpoints in longitudinal clinical trial settings.

About the Instructor: Dr. Frank Bretz is a Distinguished Quantitative Research Scientist at Novartis. He has supported the methodological development in various areas of pharmaceutical statistics, including dose finding, multiple comparisons, estimands, and adaptive designs. Frank is an Adjunct Professor at the Hannover Medical School (Germany) and the Medical University of Vienna (Austria). He was a member of the ICH E9(R1) Expert Working Group on 'Estimands and sensitivity analysis in clinical trials' and currently serves on the ICH E20 Expert Working Group on 'Adaptive clinical trials'. Frank is a Fellow of the American Statistical Association.

​

Outline: This two-day short course will include eight lectures (one hour and 30 minutes for each), with four lectures on Day 1 (October 20) and four on Day 2 (October 21).

Day 1: 
•    Introduction, motivation and scope of the ICH E9(R1) Addendum
•    A framework to align planning, design, conduct, analysis and interpretation of clinical trials
•    Description, strategies and construction of estimands
•    Generic example to illustrate the thinking process that aligns estimands and sensitivity 
Day 2: 
•    Gentle introduction to causal inference
•    Intercurrent events and missing data
•    Main analyses targeting estimands for different types of endpoints and strategies
•    Sensitivity and supplementary analysis in light of the estimand framework
 

Learning Objectives: This course will focus on estimands and related statistical methodologies that are commonly used in clinical trials. We will share our experiences and try to provide some guidance on their use in clinical trial practice. The target audience includes statisticians working in industry (pharmaceutical companies), academia (universities, medical centers, or research hospitals), or government (AIHW or TGA), and also graduate students who are interested in clinical trial methods. The difficulty level of the course is intermediate, at a second-year graduate course level. The learning objectives are three-fold: (1) to understand the fundamentals of the estimand framework and be able to apply it in clinical trials; (2) to identify an appropriate primary analysis method that targets the estimand of interest, fully aligned with the ICH E9(R1) Addendum; and (3) to implement appropriate main and sensitivity analyses.  

29th July 2022, 1.30 - 4.30pm:

APBG Mid Year Meeting 

The George Institute, The HUB, Level 5, 1 King St, Newtown

FREE event! Please RSVP to apbgsteering@gmail.com

All members and guests are invited to join us in person for refreshments and networking. The event will also be available to join online.

Date/Time
29th July 2022, 1.30-4.30pm

Location
The George Institute, The HUB, Level 5, 1 King St, Newtown

Agenda
1.30pm Tea, coffee and networking
2pm Dr Elisa Young – Getting to the CORE of CDISC
3pm Afternoon tea and networking
3.30pm Dr Helen Ogden – Flexible Models for Clustered Data
4.30pm Meeting Close

Getting to the CORE of CDISC

Speaker: Dr Elisa Young (Accelegan)

Abstract: The impact of CDISC standards, guidelines and initiatives on statistical programming over the last decade has been nothing short of revolutionary, stretching across clinical, non-clinical and observation science.  CDISC is on a continuous journey of change, with the aim of delivering new sources of data and technology platforms.  These objectives are being realised through organisational collaborations and, most importantly, a global network of volunteers.  During this presentation I’ll be discussing my experience as a volunteer on the CDISC CORE initiative, including a demonstration of the conformance validator.  I’ll also provide an update on other key CDISC initiatives.

Biography: Elisa is the Head of Biostatistics at Accelagen.  Elisa earned a PhD in Pharmacology, followed by a Masters’ in Applied Statistics, and worked in various roles within the biotech/pharma industry, from laboratory management, bench-top science, project management and data management, before settling on a career in statistics and statistical programming.  With a keen interest in CDISC, Elisa was the first Australian to obtain CDISC Tabulate Certification and is currently volunteering on the CDISC Core Project.

Flexible models for clustered data

Speaker: Dr Helen Ogden (University of Southampton)

Abstract: A wide variety of approaches are available for modelling clustered data: from assuming a single shared model for all clusters to fitting entirely separate models for each cluster. Random effects models lie between these two extremes, allowing simple variation in the model for each cluster, such as shifting a global response curve up or down by a constant (random intercept) or straight line (random slope). When the global response curve is not a straight line, these simple models sometimes fail to capture the variation in the shape of the cluster-specific response curves. I will give examples of this problem, and describe an extension to the simple random effects model which is designed to capture other types of variation.

Biography: Helen Ogden is a Lecturer in Statistics at the University of Southampton and a Fellow of the Alan Turing Institute for Data Science and Artificial Intelligence. Before that, she was a Research Fellow at the University of Warwick. Her research interests are in statistical modelling, theory and computation, with particular interest in mixed-effects models, models for count data, and conducting inference when the likelihood function is intractable.

​

4-5th November 2019,  2-Day workshop:

Network meta-analysis and population adjustment for decision-making 

Presented by David Phillippo at the Macquarie University Sydney Campus

Day 1:

• Day 1 of this course is aimed at statisticians, health economists, decision-makers, and systematic reviewers who are already familiar with pairwise meta-analysis, and who want to extend their knowledge to NMA and population adjustment methods. Participants will develop an understanding of these methods and the required assumptions and learn to assess and critique these types of analyses.

Day 2:​

• Day 2 is aimed at those with technical experience of meta-analysis who want to apply the knowledge learned on Day 1 to hands-on practical examples. Participants will gain experience implementing NMA and population-adjusted analyses in an R package based on the Bayesian modelling language Stan.

​​

​

Network meta-analysis (NMA) is a method for combining evidence from several studies on multiple treatments of interest to provide a consistent set of relative effect estimates and is widely used for healthcare decision-making and guideline development. More recently, population adjustment methods have been proposed that use individual patient data from one or more studies to relax the assumptions of NMA and adjust for differences in effect modifying variables between populations, or even to incorporate disconnected networks and single-arm studies. The methods are becoming increasingly common in technology appraisal submissions to reimbursement agencies and raise new questions and challenges for analysts anddecision-makers.

​

Our workshop presenter is David Phillippo, a Senior Research Associate in Statistics at the University of Bristol, UK. His research focuses on methodology for evidence synthesis, Bayesian Network Meta-Analysis (NMA), population adjustment methods for indirect comparisons, and accounting for bias in clinical guidelines. He is the lead author of a recent Technical Support Document published by the NICE Decision Support Unit on population-adjusted indirect comparisons, and has developed new methods extending the NMA framework to incorporate population adjustment combining individual patient data and published summary data.

​

For more information and to register, please click https://statsoc.org.au/event-3334476