Hagerty, Michael R.
September 1986
Marketing Science;Fall86, Vol. 5 Issue 4, p298
Academic Journal
Formulas are derived which estimate the accuracy of conjoint analysis in predicting preferences in a validation sample. This accuracy turns out to depend on (among other things) which model of preference is used (e.g., whether interactions are added, whether partworth or linear functions are used). I first show a paradoxical result that simpler models often yield higher predictive accuracy, even when a more complex model ts the true one. The reason for this is that the additional parameters of the complex model are estimated with larger variance, which tends to overwhelm the benefits of using the true model. I then shift my criterion from predicting an individual's preferences, to predicting market share, which is of most interest to managers. Under this criterion my conclusions reverse, and I show that a true model (even when complex) is much more likely to yield higher predictive accuracy than a simpler incorrect model. This reverses some previous conclusions in marketing, and confirms that finding the correct model of consumer preference is important in improving prediction. Results from four previous empirical papers are correctly predicted by these formulas, as well as results from additional Monte Carlo studies.


Related Articles

  • Multiattribute Judgments Under Uncertainty: A Conjoint Measurement Approach. Basu, Amiya K.; Hastak, Manoj // Advances in Consumer Research;1990, Vol. 17 Issue 1, p554 

    A methodology to predict product choice under uncertainty in attribute values is proposed and tested. The methodology consists of (i) estimating the multiattribute utility function of a consumer, and (ii) predicting new product evaluation based on expected utility computed using äie estimated...

  • Near Optimal Solutions for Product Line Design and Selection: Beam Search Heuristics. Nair, Suresh K.; Thakur, Lakshman S.; Kuang-Wei Wen // Management Science;May95, Vol. 41 Issue 5, p767 

    Many practical product line design problems have large numbers of attributes and levels. In this case, if most attribute level combinations define feasible products, constructing product lines directly from part-worths data is necessary. For three typical formulations of this important problem,...

  • Conjoint analysis helps in sorting out consumers' weiqhting of product attributes. Fetell, Howard A.; Hupfer, Herbert // Marketing News;1/28/77, Vol. 10 Issue 14, p10 

    The article focuses on conjoint analysis as a potential solution to market research problems. It is being identified as tradeoff analysis which refers to any analytical methodology used to identify the relative value to consumers of one product benefit over the other. It also helps to identify...

  • Une comparaison empirique de la validité prédictive de la méthode de composition, de l'analyse conjointe et de l'analyse conjointe hybride. Meyer-Waarden, Lars; Zeitoun, Helen // Recherche et Applications en Marketing (AFM c/o ESCP-EAP);2005, Vol. 20 Issue 3, p39 

    In this article, the effectiveness of several preference elicitation techniques for predicting product choices on the individual level is evaluated: self-explicated (ACA4 phase I and II), traditional conjoint full profile (Bretton Clark's Conjoint Analyzer) and hybrid conjoint models (Sawtooth's...

  • Conjoint models cannot live on tradeoffs alone. Ogle, Robert S. // Marketing News;9/12/86, Vol. 20 Issue 19, p22 

    The article focuses on the use of conjoint analysis to model consumer preference for product and service concepts. The products or services that consumers evaluate using this methodology, for the most part, are verbal descriptions that represent actual goods and services. Reasons that abstract...

  • Conjoint analysis in marketing: New developments with implications for research and practice. Green, Paul E.; Srinivasan, V. // Journal of Marketing;Oct90, Vol. 54 Issue 4, p3 

    The authors update and extend their 1978 review of conjoint analysis. In addition to discussing several new developments, they consider alternative approaches for measuring preference structures in the presence of a large number of attributes. They also discuss other topics such as reliability,...

  • Consideration Sets in Conjoint Analysis. Jedidi, Kamel; Kohli, Rajeev // Journal of Marketing Research (JMR);Aug1996, Vol. 33 Issue 3, p364 

    The authors model product consideration as preceding choice in a segment-level conjoint model. They propose a latent-class tobit model to estimate cardinal, segment-level preference functions based on consumers' preference ratings for product concepts considered worth adding to consumers'...

  • INDIVIDUAL LOGIT MODELS FOR CONSUMER PREFERENCES. Prave, Rose S.; Ord, J. Keith // Journal of Marketing Theory & Practice;Winter94, Vol. 2 Issue 1, p27 

    Evaluates the estimation of individual-level binary preference models from conjoint-type data. Performance of individual-level logit analysis in modeling consumer choices; Comparison of binary logit model to traditional conjoint models; Instrument for the assessment of predictive efficiency of...

  • Incorporating Prior Knowledge into the Analysis of Conjoint Studies. Allenby, Greg M.; Arora, Neeraj; Ginter, James L. // Journal of Marketing Research (JMR);May95, Vol. 32 Issue 2, p152 

    The authors use conjoint analysis to provide interval-level estimates of part-worths allowing tradeoffs among attribute levels to be examined. Researchers often possess prior information about the part-worths, such as the order and range restrictions of product attribute levels. It is known, for...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics