Statistical Science


Short course on Statistical Methods for Value of Information Analysis

8-10 June 2016, University College London

This is a brand new short course, organised and run jointly by Gianluca Baio and Anna Heath (both UCL), Mark Strong (University of Sheffield) and Nicky Welton (University of Bristol). The course aims at presenting the basic ideas underpinning the analysis of the value of information as a tool to identify research priorities and uncertainty analysis, with a particular reference to health economic evaluations.

The course, which is subsidised by the MRC Network of Hubs for Trials Methodology Research and UCL, will be held at University College London on 8-10 June 2016, the week before the 16th Biennial European Conference of the Society for Medical Decision Making (a call for abstract to the conference is available here). 

In Day 1, we will introduce the main concepts and give some basic introduction to the methods. In Day 2 we will a mixture of lectures and computer practicals aimed at providing a clear understanding of the statistical methods used to perform the relevant calculations. Finally, in Day 3 we will present cutting-edge methods, recently proposed in the literature to reduce the computational burden associated with the computation of relevant quantities, such as the Expected Value of Partial Perfect Information (EVPPI). The practical sessions will use the freely available software R, the SAVI web-app and the R package BCEA.


Day 1 (8 June 2016). 9.30 - 16.30

  • 9.30-10.00: Registration and coffee
  • 10.00-10.10: Welcome and overview of the day (GB)
  • 10.10-10.40: Introduction to cost-effectiveness analysis (net-benefit, PSA, CEplanes, CEAFs) (GB)
  • 10.40-11.30: Introduction to value of information (NW)
  • 11.30-12.30: Computation of EVPI and EVPPI for a decision tree, including practical (GB) 
  • 12.30-1.15: Lunch break
  • 1.15-2.15: Case studies: EOGBS, Breast Cancer Screening, IVIG (NW)
  • 2.15-3.00: Introduction to expected value of sample information for designing new research studies (NW)
  • 3.00-3.15: Coffee break
  • 3.15-3.45: Model error and structural uncertainty (GB)
  • 3.45-4.30: Critical appraisal of VOI including group exercise (NW)

      NB: This day will be an introduction to value of information and has no pre-requisites. This day can be taken as a stand-alone course.

      Day 2 (9 June 2016). 9.00 - 16.30

      • 9.00-10.00: R refresher tutorial (*OPTIONAL*)
      • 9.30-10.00: Registration and coffee
      • 10.00-10.10: Welcome and overview of day 2 
      • 10.10-11.00: Introduction to BCEA with PRACTICAL (GB)
      • 11.00-11.45: EVPPI theory: simulation approaches (MS)
      • 11.45-12.30: PRACTICAL: EVPPI (1) (MS)
      • 12.30-1.15: Lunch break (Demo … EVPPI in R takes an hour!)
      • 1.15-2.00: Algebraic tricks for EVPPI (NW)
      • 2.00-2.45: PRACTICAL: Algebraic tricks (NW)
      • 2.45-3.00: Coffee break
      • 3.00-3.45: EVSI using conjugacy. Limitations of simulation approaches and computational challenges for EVSI (MS/NW)
      • 3.45-4.30: PRACTICAL: EVSI (NW/MS)

        NB: This day will be a mixture of lectures and computer practical. Therefore, some knowledge of computer programming is preferable, ideally in R. Knowledge of value of information methods (or attendance to Day 1) are necessary.

        Day 3 (10 June 2016). 9.30 - 16.15

        • 9.30-9.50: Coffee
        • 9.50-10.00: Welcome and overview of the day 3
        • 10.00-11.00: EVPPI theory: regression-based approaches (MS)
        • 11.00-12.00: PRACTICAL: EVPPI (2) (MS)
        • 12.00-12.45: Lunch break
        • 12.45-1.45: Advanced meta-modelling techniques (AH)
        • 1.45-2.45: PRACTICAL: Meta-modelling using BCEA and INLA (AH)
        • 2.45-3.00: Coffee break
        • 3.00-4.15: Meta-modelling approaches for EVSI (MS)

          This day follows from Day 2 and again will be a mixture of lectures and computer practicals.


          DAY 1: No pre-requisites required

          DAY 2 & DAY 3: Understanding of cost-effectiveness analysis, the basic concepts of value of information measures (EVPI, EVPPI, EVSI), experience of computer programming (preferably but not necessarily R), some training in statistical methods.

          Registration information

          Registration to the workshop is subject to the following fees: 

          • For 3 days: £300 (£150 for students)
          • For 1st day: £100 (£50 for students)
          • For 2nd and 3rd days: £200 (£100 for students)

          This course is subsidised by MRC Network of Hubs for Trials Methodology Research and UCL. Travel bursaries are also available for students and hub network members, courtesy of the MRC Network of Hubs for Trials Methodology Research. To apply, contact g.baio@ucl.ac.uk. Two free places available per hub.

          This course is now full for Days 2 and 3. You can still register for Day 1 online by visiting the UCL store here.

          Places available: 70 for Day 1; 30 for Days 2 and 3.