B0905
Title: Discrete choice experiments: An overview on constructing D-optimal and near-optimal choice sets
Authors: Abdulrahman Sultan S Alamri - RMIT University (Australia) [presenting]
Abstract: Discrete choice experiments (DCEs) help to identify the underlying influences on an individual's choice behaviour. With continued developments in DCE methods, DCEs recently are considered the primary data source for decision-makers in various fields, e.g., health resources, marketing, transport, economics, and the list goes on. DCEs are based on stated preference, thus the construction technique of DCE has an obvious effect on the outputs of stated choice. The developments in the field of research nowadays are occurring at a tremendous speed which makes it hard for many to be at the forefront of research and keep up with the state-of-the-art. The question in many practitioners' minds is which techniques perform better (i.e. given small designs with high efficiency) in a given circumstance. To address these concerns, we compile the most efficient techniques for constructing optimal and near-optimal reduced choice sets of main effects only, under the assumption that all alternatives (options) per choice set are equally attractive. The aim is to review and to compare the known theoretical/mathematical constructions of DCEs from known combinatorial and statistical designs in the literature, such as Hadamard matrices, BIBDs, orthogonal arrays, fractional factorial designs. Also, suggesting potential areas for ongoing research in this direction.
