Being Careful with Conjoints: Methods to Account for Inattentiveness

• In Event: Conjoint Design in Focus: Practical and Theoretical Advances

Abstract

Recent research highlights substantial levels of inattentiveness in online, survey-based experiments. Importantly, such inattentiveness threatens to bias treatment effect estimates toward zero. This problem is likely even more pronounced in conjoint experiments, which ask respondents to attend to an even larger amount of information. In this paper, we explore potential ways to both measure--and account for--respondent inattentiveness in conjoint experiments. Replicating published conjoint experiments with large national samples, we ultimately propose a novel method--"conjoint attention checks" (CACs)--to both measure respondents' level of attentiveness and to provide for more robust tests of hypotheses in conjoint experiments.

Authors

• Mia Costa, Dartmouth College

• John V. Kane, New York University