Pre-Conference Courses

At the 2019 PSI Conference, there will be the following two Pre-Conference Courses taking place on the Sunday afternoon. 

Date: Sunday 2nd June 2019
Time: 13:00 - 17:00
Pre-Conference Courses:

  1. Stated Preference Methods: Eliciting patient preferences in the age of personalized medicine
  2. Evidence Synthesis for Clinical Trials: Use of Historical Data and Extrapolation - Methods, applications and implementation with the R package RBesT


1. Stated Preference Methods: Eliciting patient preferences in the age of personalized medicine


Course Presenters: 

Shahrul Mt-Isa (MSD)

Maria Costa (Novartis)

Marco Boeri (RTI)

Mike Colopy (UCB)

Ursula Garczarek (Cytel)

Alexander Schacht (Lilly)

Gaelle Saint-Hillary (Servier and Polytechnic University of Turin) 

Course Description:

Many crucial questions need to be answered throughout drug development: “which efficacy measures best represent clinically meaningful outcomes?”, “which adverse events should be monitored closely?”, “what drives the decision: maximizing efficacy or reducing the risk of adverse events?”

The answers to these questions reflect an element of judgment by the clinical team. To enhance transparency and increase robustness of the decision-making process additional viewpoints can be included. With this in mind, pharmaceutical companies can conduct preference elicitation studies as part of clinical development programs to assess how the benefit-risk trade-off of a new drug will impact various stakeholders. Typically, these studies focus on patient preferences, in an effort to bring the patients’ view into the drug development process, but other stakeholders, such as physicians, can also be included in the assessment.

Although regulatory agencies have started discussing how to use preference elicitation to support decision-making, and new draft guidelines are now open for public consultation, statisticians have not yet been engaged on this topic. Preference data present new challenges for many statisticians. If you have limited experience yourself on this topic, then you are not alone. At the end of this course you should be able to understand the advantages and challenges characterizing preference elicitation, how it relates to benefit-risk assessment, and how to apply it to your own project.

There is no pre-requisite for the course, but attendees are assumed to be familiar with statistical methods in the drug development lifecycle.

Target Audience:

Statisticians in the pharmaceutical industry or with an interest in preference studies or decision science.

Goals of the Course:

To understand when and how to conduct stated preference studies and the different preference elicitation approaches:

  • Identify the need for a preference study, and plan a preference study
  • Understand the feasibility and complexity of eliciting and using preferences for benefit-risk decisions
  • Communicate the results 
The course will include a hands-on workshop where participants will have the opportunity to learn about preference elicitation approaches, and the advantages and challenges with patient preference elicitation from the design of the study to the analysis of the data and its interpretation. No prior knowledge of any  software is required.

2. Evidence Synthesis for Clinical Trials: Use of Historical Data and Extrapolation - Methods, applications and implementation with the R package RBesT


Course Presenters: 

Sebastian Weber 

Satrajit Roychoudhury 

Course Description:

A Bayesian approach provides the formal framework to incorporate external information into the statistical analysis of a clinical trial. There is an intrinsic interest of leveraging all available information for an efficient design and analysis of clinical trials. The use of external data in trials are nowadays used in earlier phases of drug development (Trippa, Rosnerand Muller, 2012; French, Thomas and Wang, 2012; Hueber et al., 2012), occasionally in phase III trials (French et al., 2012), and also in special areas such as medical devices (FDA, 2010a), orphan indications (Dupont and Van Wilder, 2011) and extrapolation in pediatric studies (Berry, 1989). This allows trials with smaller sample size or with unequal randomization (more subjects on treatment than control). In this short course, we'll provide a statistical framework to use trial external evidence to better plan and/or incorporate external information into a trial.

During the first part of the course we will introduce the meta-analytic predictive (MAP) model (Neuenschwander, 2010). The MAP model is a Bayesian hierarchical model, which combines the evidence from different potentially heterogeneous sources (usually studies). The MAP model provides a prediction for a future study based on available information while accounting for inherent heterogeneity in the data. This approach can be used in widely different applications of biostatistics.

In the second part of the course we will focus on key applications of the MAP approach in biostatistics, which are (i) the derivation of informative priors from historical controls and (ii) probability of success. These applications will be demonstrated using the R package RBesT, the R Bayesian evidence synthesis tools, which are freely available from CRAN. During the second part hands-on exercises will be part of the course to enable participants to apply the presented approach themselves.

Target Audience:


The target audience of the course are statisticians in the pharmaceutical industry interested in applications of the meta-analytic approach which include informative prior derivation for early phase programs or probability of success calculations for drug development programs (phase I/II/III).

Goals of the Course:

To understand the foundations of the meta-analytic framework and its application to key drug development problems:

  • Derivation of informative priors to reduce the control group sample size
  • Trial design evaluation when using informative priors (type I error, power)
  • Understand the concept of a robust trial design
  • Probability of success for drug development programs

The course will include hands-on sessions which will teach participants how to apply the meta-analytic approach in practice at the example of real case-studies. The hands-on session will be based on the R package R Bayesian evidence synthesis tools (RBesT). While familiarity with R is helpful, all hands-on exercises will be based on extensive example code such that SAS users are very welcome to join the course.


 Registration Type Early bird registration fee
(until 20 March 2019)
Full registration fee
(from 21 March 2019)
PSI member Pre-conference course
(1 or 2)
£255  £295
Non-member Pre-conference course
(1 or 2)
£300  £340

Registration for both courses is available through the conference registration site. Places on each course will be limited, so book early to avoid disappointment!  

Website Banner Template

EventsFuture Events

  • PSI Webinar: Adaptive design: updated draft FDA guidance and its implications - Dates: 11 – 11 Jun, 2019

    In September 2018 the FDA published a guidance on adaptive design for clinical trials of drugs and biologics, updating (not finalizing) its initial draft from February 2010. The main focus of the webinar will be to provide an overview of its main contents, which will be presented by Jürgen Hummel (PPD). In addition, Kaspar Rufibach (Roche) will introduce an open-source statistical software for adaptive designs, RPACT (an R package that enables the design and analysis of confirmatory adaptive clinical trials). Kit Roes will also comment on the guidance from a European Regulatory perspective, which will be followed by a brief panel discussion.
  • Adaptive Designs - Dates: 24 – 24 Jun, 2019

    During this meeting we will hear about adaptive sample allocation for phase II/III designs, a new CONSORT extension reporting guideline for adaptive designs, regulatory aspects and case studies.
Pharm Research Associates

Principal Biostatistician


Autolus Therapeutics

Head of Statistical and Data Innovation as Head of Biometrics



Leading Biostatistician with experience in Big Data and advanced analytics



Biostatistician with experience in clinical drug development



Statistician Opportunities in the UK