Recent research suggests that using orthogonal arrays in full-profile conjoint may fail to provide adequate internal validity when the validation set consists of Pareto optimal profiles or when prices covary with the rest of the profiles' attribute levels. This study's findings indicate that partworths calibrated in the wrong environment predict a holdout sample as well as those calibrated in the correct (validation) environment do.
No takes yet. Share an insight, caveat, or question.
Green et al. (1988) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: