28 June 2026, 1:30 PM – 4:55 PM | 13:30 – 16:55 (local time)
Faculty
- Jeremy Goldhaber-Fiebert, PhD – Professor of Health Policy, Stanford University, United States
- Natalia Kunst, PhD – Associate Director, Global HEOR, Bristol Myers Squibb; Adjunct Assistant Professor, Yale School of Medicine, United States
Course Overview
This course presents computational methods for the Expected Value of Sample Information (EVSI), a decision-theoretic measure of the monetary value of collecting additional information through potential future research. Participants will explore how EVSI can be used to support research prioritization and inform the design of future studies.
Based on health economic decision models, EVSI quantifies the expected value of conducting additional research and allows comparison with the cost of that research to determine whether it is likely to yield a positive net benefit. Despite its conceptual advantages, EVSI has historically been difficult to implement due to computational complexity, limiting its use in practice.
Recent methodological advances have reduced this computational burden, enabling practical estimation of EVSI. This course introduces these advances and provides a demonstration of how to efficiently compute EVSI using R. The course also highlights ongoing efforts from the Collaborative Network for Value of Information (ConVOI) to improve the accessibility and application of EVSI methods in research prioritization and study design.
Learning Objectives
Participants will learn how to:
- Distinguish four recently developed calculation methods for EVSI
- Determine which EVSI calculation method is appropriate for a given health economic decision model
- Calculate EVSI in R for different types of health economic models
- Present EVSI analyses using standardized, publication-quality graphics
- Discuss key assumptions for calculating the Expected Net Benefit of Sampling (ENBS)
- Design efficient future research studies by determining optimal sample sizes
Course Format
This half-day course combines lectures and practical exercises. Lectures will introduce EVSI as a tool for research prioritization and study design, along with recently developed computational methods.
The practical component will focus on implementing these methods using prepared R code. Participants will work through examples using the EVSI R package to gain hands-on experience applying the techniques discussed.
Participant Requirements
Participants should have:
- Experience using R
- Knowledge of probabilistic health economic modeling
- Prior exposure to value of information analysis
Some knowledge of Bayesian statistical methods is helpful but not required.
Participants who wish to follow along with the coding exercises should bring a laptop with updated versions of R and RStudio installed.talled.