Discrete choice experiments in health economics: a review of the literature

Abstract

Background: Discrete choice experiments (DCEs) are increasingly used in health economics to address a wide range of health policy-related concerns.

Objective: Broadly adopting the methodology of an earlier systematic review of health-related DCEs, which covered the period 2001-2008, we report whether earlier trends continued during 2009-2012.

Methods: This paper systematically reviews health-related DCEs published between 2009 and 2012, using the same database as the earlier published review (PubMed) to obtain citations, and the same range of search terms.

Results: A total of 179 health-related DCEs for 2009-2012 met the inclusion criteria for the review. We found a continuing trend towards conducting DCEs across a broader range of countries. However, the trend towards including fewer attributes was reversed, whilst the trend towards interview-based DCEs reversed because of increased computer administration. The trend towards using more flexible econometric models, including mixed logit and latent class, has also continued. Reporting of monetary values has fallen compared with earlier periods, but the proportion of studies estimating trade-offs between health outcomes and experience factors, or valuing outcomes in terms of utility scores, has increased, although use of odds ratios and probabilities has declined. The reassuring trend towards the use of more flexible and appropriate DCE designs and econometric methods has been reinforced by the increased use of qualitative methods to inform DCE processes and results. However, qualitative research methods are being used less often to inform attribute selection, which may make DCEs more susceptible to omitted variable bias if the decision framework is not known prior to the research project.

Conclusions: The use of DCEs in healthcare continues to grow dramatically, as does the scope of applications across an expanding range of countries. There is increasing evidence that more sophisticated approaches to DCE design and analytical techniques are improving the quality of final outputs. That said, recent evidence that the use of qualitative methods to inform attribute selection has declined is of concern.