Experimental designs involve breaking down a product into a set of attributes, then assembling the attributes into a set of hypothetical products that are presented to respondents. Designing choice sets for discrete-choice models poses a special set of considerations beyond those of classical design of experiments (DOE).
A body of statistical work covers design of experiments. A good starting point for exploring the topic is our tutorial on experimental designs for choice models. Based on Warren Kuhfeld's paper on the subject, cited below, this tutorial covers the key issues in relatively simple, non-technical language.
There are so many papers on this subject that we recommend Googling the term "design of choice experiments" for current papers. We list a few of them here.
- Burgess, Leonie and Deborah J. Street (June 19, 2003), "Optimal Designs for Choice Experiments with Asymmetric Attributes", Department of Mathematical Sciences, University of Technology Sydney.
- ______ (2003), "Optimal Designs for 2k Choice Experiments", Department of Mathematical Sciences, University of Technology Sydney.
- Hauser, John R. and Olivier Toubia (2003), "Properties of Preference Questions: Utility Balance, Choice Balance, Configurators, and M-Efficiency", MIT Center for Innovation in Product Development.
- Huber, J. and Zwerina, K. (1996), "The Importance of Utility Balance in Efficient Choice Designs", Journal of Marketing Research, 33 (August), 307-317.
- Kuhfeld, Warren F., Randall D. Tobias, Mark Garratt, "Efficient Experimental Design with Marketing Research Applications", Journal of Marketing Research (November, 1994), pp. 545-557.
- ______, "Experimental Design, Efficiency, Coding, and Choice Designs", SAS Technical Paper TS-694C
- Street, Deborah J., and Leonie Burgess (2003), "Optimal and Near-Optimal Pairs for the Estimation of Effects in 2-level Choice Experiments", Dept. of Mathematical Sciences, University of Technology, Sydney.
- ______, "Quick and Easy Choice Sets: Using Word Processing Packages to Construct Near-Optimal Stated Choice Experiments", International Journal of Research in Marketing, Vol. 22, No. 4. (2005), pp. 459-470.
In recent years a number of texts covering the design of choice experiments have emerged. Here is a list of the leading ones
- Kuhfeld, Warren. Marketing Research Methods in SAS, SAS Technical Paper TS-689. Essential reference for choice modelers using SAS, and the paper on which our tutorial is based.
- Louviere, Jordan, J., David A. Hensher, Joffre D. Swait, Stated Choice Methods: Analysis and Application. Cambridge, England: Cambridge University Press, 2000. ISBN 0-521-78275-9. All-in-one textbook for practical application of discrete-choice models
- Street, Deborah and Leonie Burgess, The Construction of Optimal Stated Choice Experiments. Hoboken, New Jersey: John Wiley & Sons, 2007. ISBN 978-0-470-05332-4. The most comprehensive, up-to-date text on choice designs.