We provide a user guide on the analysis of data (including best-worst and best-best data) generated from discrete choice experiments (DCEs), comprising a theoretical review of the main choice models followed by practical advice on estimation and post estimation. We also provide a review of standard software. In providing this guide we endeavor not only to provide guidance on choice modeling, but to do so in a way that provides researchers to the practicalities of data analysis. We argue that choice of modeling approach depends on: the research questions; study design and constraints in terms of quality/quantity of data and that decisions made in relation to analysis of choice data are often interdependent rather than sequential. Given the core theory and estimation of choice models is common across settings, we expect the theoretical and practical content of this paper to be useful not only to researchers within but also beyond health economics. Compliance with Ethical StandardsNo funding was received for the preparation of this paper. Emily Lancsar is funded by an ARC Fellowship (DE1411260). Emily Lancsar, Denzil Fiebig and Arne Risa Hole have no conflicts of interest. 2 Key Points for Decision Makers We provide a user guide on the analysis of data, including best-worst and best-best data, generated from DCEs, addressing the questions of DCE  We provide a theoretical overview of the main choice models and review three standard statistical software packages: Stata; Nlogit; and Biogeme.  Choice of modeling approach depends on the research questions; study design and constraints in terms of quality/quantity of data and decisions made in relation to analysis of choice data are often interdependent rather than sequential.  A health based DCE example for which we provide the data and estimation code is used throughout to demonstrate the data set up, variable coding, various model estimation and post estimation approaches.3

Although vaccination characteristics proved to influence influenza vaccination uptake, certain patient characteristics had an even higher impact on influenza vaccination uptake. Policy makers and general practitioners can use these insights to improve their communication plans and information regarding influenza vaccination for individuals aged 60 years or older. For instance, physicians should focus more on patients who had experienced side effects due to vaccination in the past, and policy makers should tailor the standard information folder to patients who had been vaccinated last year and to patient who had not.

A 20% sugar-sweetened beverage price increase was associated with a reduction in their purchases and an increase in purchases of healthier alternatives. Community retail settings present a bottom-up approach to improving consumer beverage choices.

No abstract

BackgroundA discrete choice experiment (DCE) is a method used to elicit participants’ preferences and the relative importance of different attributes and levels within a decision-making process. DCEs have become popular in healthcare; however, approaches to identify the attributes/levels influencing a decision of interest and to selection methods for their inclusion in a DCE are under-reported. Our objectives were: to explore the development process used to select/present attributes/levels from the identified range that may be influential; to describe a systematic and rigorous development process for design of a DCE in the context of thrombolytic therapy for acute stroke; and, to discuss the advantages of our five-stage approach to enhance current guidance for developing DCEs.MethodsA five-stage DCE development process was undertaken. Methods employed included literature review, qualitative analysis of interview and ethnographic data, expert panel discussions, a quantitative structured prioritisation (ranking) exercise and pilot testing of the DCE using a ‘think aloud’ approach.ResultsThe five-stage process reported helped to reduce the list of 22 initial patient-related factors to a final set of nine variable factors and six fixed factors for inclusion in a testable DCE using a vignette model of presentation.ConclusionsIn order for the data and conclusions generated by DCEs to be deemed valid, it is crucial that the methods of design and development are documented and reported. This paper has detailed a rigorous and systematic approach to DCE development which may be useful to researchers seeking to establish methods for reducing and prioritising attributes for inclusion in future DCEs.Electronic supplementary materialThe online version of this article (10.1186/s12913-018-3305-5) contains supplementary material, which is available to authorized users.