Discrete Choice Experiment
A discrete choice experiment (DCE) is a stated-preference method in which respondents repeatedly choose their preferred option from sets of alternatives described by systematically varied attributes, allowing the analyst to estimate how each attribute drives choice. Grounded in McFadden's random utility theory and operationalized for designed experiments by Louviere and Woodworth in 1983, the DCE treats each choice as the selection of the alternative with the highest latent utility and recovers the utility coefficients from observed choices. Because attributes are varied independently by experimental design, the method isolates the marginal effect of each attribute, including price, and yields marginal rates of substitution such as willingness to pay. DCEs are analyzed with multinomial (conditional) logit and, increasingly, with mixed and nested logit models that relax restrictive assumptions and capture preference heterogeneity. The approach is essentially the same machinery as choice-based conjoint but is the standard term in transport, health, and environmental economics, where it is used to value non-market goods. Its rigor and flexibility have made it a dominant stated-preference technique across the social sciences.
Registro de origem
Citações copiadas literalmente do registro de origem do método. Nenhuma verificação em nível de alegação é inferida delas.
- Louviere, J. J., & Woodworth, G. (1983). Design and Analysis of Simulated Consumer Choice or Allocation Experiments: An Approach Based on Aggregate Data. Journal of Marketing Research, 20(4), 350-367. · DOI 10.1177/002224378302000403
- Hensher, D. A., Rose, J. M., & Greene, W. H. (2015). Applied Choice Analysis (2nd ed.). Cambridge: Cambridge University Press. · ISBN 9781107465923
- Train, K. E. (2009). Discrete Choice Methods with Simulation (2nd ed.). Cambridge: Cambridge University Press. · ISBN 9780521766555
Alegações curadas
Alegações persistidas no livro-razão de evidências, cada uma com sua própria avaliação.
Esta visualização não inventa uma avaliação de alegação quando o livro-razão não a possui.
Métodos relacionados
Gerado a partir do grafo de métodos e mostrado como relações sugeridas por máquina — nenhuma alegação de evidência é inferida.