Optimal two-level conjoint designs with constant attributes in the profile sets
Journal of Statistical Planning and Inference , Volume 140 - Issue 11 p. 3035- 3046
We propose a simple strategy to construct D-, A-, G- and V-optimal two-level designs for rating-based conjoint studies with large numbers of attributes. In order to simplify the rating task, the designs hold one or more attributes at a constant level in each profile set. Our approach combines orthogonal designs and binary incomplete block designs with equal replication. The designs are variance-balanced meaning that they yield an equal amount of information on each of the part-worths.
|Balanced and partially balanced incomplete block designs, Binary incomplete block designs, Comparison depth, D-, A-, G- and V-optimality, Orthogonal designs, Two-level conjoint design|
|Journal of Statistical Planning and Inference|
|Organisation||Erasmus Research Institute of Management|
Kessels, R, Goos, P.P, & Vandebroek, M. (2010). Optimal two-level conjoint designs with constant attributes in the profile sets. Journal of Statistical Planning and Inference, 140(11), 3035–3046. doi:10.1016/j.jspi.2010.04.007