Although data collection in conjoint analysis has traditionally involved the use of in-person interviews, recent years have seen a trend toward the use of alternative data collection modes, including mail questionnaires and telephone interviews. Since these alternative modes differ in environment, the author examines the predictive performance of conjoint models under three data collection modes, i.e., in-person interviews, mail questionnaire, and telephone interviews. The results indicate the conjoint models examined to be comparable in predictive, performance across the three data collection modes.