Structural Reliability and Stability of Nonmetric Conjoint Analysis

Abstract

Structural reliability and stability of nonmetric conjoint analysis are examined under conditions of severe structural perturbation and substantial variation in the number of stimulus profiles. The individual-level part worth functions are jackknifed. The jackknifed parameters, derived relative importance weights, and standard errors of estimated parameters are examined across the different treatment conditions. The results indicate that conjoint analysis is a fairly robust procedure for assessing an individual's preferences.