Technical Papers
Title: Adaptive Choice-Based Conjoint Description: Choice-Based Conjoint has most always involved fixed, or non-adaptive experimental design plans. Some research on adaptive plans has been presented in the past, but adaptive experimental designs for choice-based conjoint have not found widespread use. The authors (Johnson, Huber, and Bacon) describe a new design approach that uses prior utility information about the attribute levels to design new statistically informative questions. The general idea is that the determinant of the information matrix can be expressed as the product of the characteristic roots of the matrix, and the biggest improvement comes from increasing the smallest roots. Thus, new choice tasks with design vectors that mirror the characteristic vectors corresponding to the smallest roots are quite efficient in maximizing precision. The authors conducted a split-sample study. They found that the ACBC led to improvements in share predictive accuracy of holdout choice tasks. There were no little or no differences in the treatments in terms of hit rates. This paper was presented at the 2003 Sawtooth Software Conference.Download: |
 Applied methodologiesTechnical papers |
#03
International Market Research Agency
#03 "The overall performance of SKIM is great, they met our objectives and we were impressed that SKIM
could deliver the data so fast"
|
Download this technical paper