Adaptive Designs for Likert-Type Data: An Approach for Implementing Marketing Surveys

Abstract

The authors discuss a method for implementing marketing surveys in which the questionnaire is “adapted” to the individual respondent. This approach (referred to as “adaptive design”) enables the researcher to pose to the respondent only those scale items (usually a subset of the entire scale) that provide useful “information” about his or her attitude. Such adaptive designs are based on a measurement theory, the Latent Trait Theory (LTT), which has been developed largely in the areas of education and psychology. However, much previous research has focused on adaptive designs that are based on binary LTT models. The authors take the first step in examining adaptive designs for Likert-type data within a marketing context. Initially they discuss and evaluate the graded-response LTT model that utilizes all of the information in Likert-type items. Then, using a simulation study, they apply the graded LTT model to implement an adaptive design for the measurement of consumer discontent. The results of the simulation suggest that an adaptive design based on the graded-response LTT performs reasonably well on several criteria. Furthermore, the findings support theoretical predictions that adaptive designs for Likert-type data can achieve measurement efficiency and precision with a substantially smaller item pool. Implications of adaptive designs for marketing researchers and practitioners, and of LTT in general, are discussed.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 68 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.