Discrete Choice Analysis in Health Economics

Discrete choice analysis encompasses a suite of quantitative methods for eliciting and modelling individual preferences concerning healthcare goods, services and policies. At its core lies the discrete choice experiment (DCE), which presents respondents with hypothetical scenarios characterised by varying attributes and asks them to choose their preferred option. The underlying random utility framework permits estimation of the relative importance of attributes, trade-offs individuals are willing to make and predicted uptake of innovations or interventions. Designs typically involve careful attribute selection via literature review and stakeholder engagement, followed by experimental construction of choice sets under principles of efficiency and orthogonality. Estimates are obtained using econometric models such as conditional logit, mixed logit and latent class analysis, enabling heterogeneity in tastes and segmentation of populations. Applications range from valuing new medicines and diagnostic tests to informing health workforce incentives, digital health adoption and priority setting under constrained budgets. Discrete choice methods have gained global traction in informing health technology assessment, pricing strategies, resource allocation and equity-sensitive decisionmaking. A growing literature explores methodological refinements—such as inclusion of opt-out options, dual-response designs and advanced modelling of scale heterogeneity—and assesses the external validity of stated preferences against real-world behaviour. The insights derived from discrete choice studies support policymakers in designing interventions that align with patient and provider preferences, thus enhancing uptake, satisfaction and ultimately health outcomes.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Discrete Choice Analysis in Health Economics publication trend

The graph below shows the total number of articles in discrete choice analysis in health economics across all publications each year (not limited to Nature Index journals).

Technical terms

Discrete Choice Experiment (DCE): A stated-preference method presenting hypothetical alternatives defined by attributes and levels to infer trade-offs and attribute importance.

Best–Worst Scaling (BWS): A preference elicitation technique in which respondents identify the most and least important items within choice sets, enhancing discrimination among attributes.

Mixed Logit Model: An econometric approach that accounts for random variation in preferences across individuals and correlation over repeated choices.

Latent Class Analysis (LCA): A segmentation method that uncovers unobserved subgroups within a sample based on similar choice patterns, capturing discrete heterogeneity.

Opt-out Option: A design feature allowing respondents to choose no available alternative, reflecting realistic non-selection behaviour and reducing forced or artificial choices.

References

1. Investigating Individuals’ Preferences in Determining the Functions of Smartphone Apps for Fighting Pandemics: Best-Worst Scaling Survey Study. Journal of Medical Internet Research (2023).
2. Preferences for Mobile App Features to Support People Living With Chronic Heart Diseases: Discrete Choice Study. JMIR mHealth and uHealth (2025).
3. How well do discrete choice experiments predict health choices? A systematic review and meta-analysis of external validity. The European Journal of Health Economics (2018).
4. The Effect of Including an Opt-Out Option in Discrete Choice Experiments. PLOS ONE (2014).
5. Experimental measurement of preferences in health and healthcare using best-worst scaling: an overview. Health Economics Review (2016).