Workshop: Conducting Economic Evaluation Using Person-Level Data

In an environment with constrained resources, understanding the value for money of a health intervention (e.g., medication, medical device) could support the process for funding and resource allocation decisions.Several analytical approaches and data sources can be used to assess the ‘value for money’ of health interventions. Although aggregate data are often used to populate decision analytic models to show the value for money of the intervention of interest, they remove variability within groups and rely on certain assumptions.

In today’s context, with the emergence of real-world evidence, person-level data (such as those obtained from administrative databases, clinical trials, or observational studies) are becoming more accessible. This workshop will introduce how we could use person-level data to conduct an economic evaluation of a health intervention. Regression techniques can be applied to a health economics analysis and used to estimate incremental cost-effectiveness ratio and incremental net benefit. The use of regression analysis is attractive for a number of reasons such as the fact that it allows the adjustment of potential confounders and the investigation of whether the value for money of health interventions varies across population subgroups. This workshop will illustrate the concepts and potential roles of person-level data in health technology assessment.

• To understand how to conduct cost-effectiveness analysis using person-level data and regression technique
• To explore techniques for characterizing the uncertainty in person-level cost-effectiveness analysis
• To explain the results of person-level cost-effectiveness analyses in a way that improves the chances of them being understood

The workshop will introduce a method for estimation and uncertainty of cost-effectiveness statistics using person-level data. The focus is on techniques to create and explain economic information from person-level data (e.g., from clinical trials, observational studies, or administrative databases).