Chapter

Principles of Forecasting

Volume 30 of the series International Series in Operations Research & Management Science pp 147-167

Forecasting with Conjoint Analysis

  • Dick R. WittinkAffiliated withYale School of Management
  • , Trond BergestuenAffiliated withAmerican Express

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Conjoint analysis is a survey-based method managers often use to obtain consumer input to guide their new-product decisions. The commercial popularity of the method suggests that conjoint results improve the quality of those decisions. We discuss the basic elements of conjoint analysis, describe conditions under which the method should work well, and identify difficulties with forecasting marketplace behavior. We introduce one forecasting principle that establishes the forecast accuracy of new-product performance in the marketplace. However, practical complexities make it very difficult for researchers to obtain incontrovertible evidence about the external validity of conjoint results. Since published studies typically rely on holdout tasks to compare the predictive validities of alternative conjoint procedures, we describe the characteristics of such tasks, and discuss the linkages to conjoint data and marketplace choices. We then introduce five other principles that can guide conjoint studies to enhance forecast accuracy.

Keywords

Conjoint analysis validation measures forecasts at aggregate and individual levels