A Full Bayesian Model to Handle Structural Ones and Missingness in Economic Evaluations from Individual-Level Data

TL;DR

This paper introduces a comprehensive Bayesian model for economic evaluations from individual-level data, effectively addressing issues like non-normality, spikes, and missing data to improve inference accuracy.

Contribution

It presents a novel Bayesian framework that handles complex data features in economic evaluations, demonstrating its advantages over standard methods.

Findings

The Bayesian model effectively manages spikes and missingness in data.

Sensitivity analysis shows robustness of conclusions under various missingness assumptions.

Application to the MenSS trial illustrates improved inference accuracy.

Abstract

Economic evaluations from individual-level data are an important component of the process of technology appraisal, with a view to informing resource allocation decisions. A critical problem in these analyses is that both effectiveness and cost data typically present some complexity (e.g. non normality, spikes and missingness) that should be addressed using appropriate methods. However, in routine analyses, simple standardised approaches are typically used, possibly leading to biased inferences. We present a general Bayesian framework that can handle the complexity. We show the benefits of using our approach with a motivating example, the MenSS trial, for which there are spikes at one in the effectiveness and missingness in both outcomes. We contrast a set of increasingly complex models and perform sensitivity analysis to assess the robustness of the conclusions to a range of plausible missingness assumptions. This paper highlights the importance of adopting a comprehensive modelling approach to economic evaluations and the strategic advantages of building these complex models within a Bayesian framework.