Dynamic models incorporating individual heterogeneity

Utility evolution in conjoint analysis

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

It has been shown in the behavioral decision making, marketing research, and psychometric literature that the structure underlying preferences can change during the administration of repeated measurements (e.g., conjoint analysis) and data collection because of effects from learning, fatigue, boredom, and so on. In this research note, we propose a new class of hierarchical dynamic Bayesian models for capturing such dynamic effects in conjoint applications, which extend the standard hierarchical Bayesian random effects and existing dynamic Bayesian models by allowing for individual-level heterogeneity around an aggregate dynamic trend. Using simulated conjoint data, we explore the performance of these new dynamic models, incorporating individual-level heterogeneity across a number of possible types of dynamic effects, and demonstrate the derived benefits versus static models. In addition, we introduce the idea of an unbiased dynamic estimate, and demonstrate that using a counterbalanced design is important from an estimation perspective when parameter dynamics are present.

Original languageEnglish (US)
Pages (from-to)285-293
Number of pages9
JournalMarketing Science
Volume24
Issue number2
DOIs
StatePublished - Mar 1 2005

Fingerprint

Conjoint analysis
Dynamic effects
Bayesian model
Behavioral decision making
Fatigue
Marketing research
Preference change
Psychometrics
Data collection
Random effects
Boredom

All Science Journal Classification (ASJC) codes

  • Business and International Management
  • Economics and Econometrics
  • Marketing

Cite this

@article{fff1071882c94f5492bbde9dc49a11fb,
title = "Dynamic models incorporating individual heterogeneity: Utility evolution in conjoint analysis",
abstract = "It has been shown in the behavioral decision making, marketing research, and psychometric literature that the structure underlying preferences can change during the administration of repeated measurements (e.g., conjoint analysis) and data collection because of effects from learning, fatigue, boredom, and so on. In this research note, we propose a new class of hierarchical dynamic Bayesian models for capturing such dynamic effects in conjoint applications, which extend the standard hierarchical Bayesian random effects and existing dynamic Bayesian models by allowing for individual-level heterogeneity around an aggregate dynamic trend. Using simulated conjoint data, we explore the performance of these new dynamic models, incorporating individual-level heterogeneity across a number of possible types of dynamic effects, and demonstrate the derived benefits versus static models. In addition, we introduce the idea of an unbiased dynamic estimate, and demonstrate that using a counterbalanced design is important from an estimation perspective when parameter dynamics are present.",
author = "Liechty, {John C.} and Duncan Fong and Wayne Desarbo",
year = "2005",
month = "3",
day = "1",
doi = "10.1287/mksc.1040.0088",
language = "English (US)",
volume = "24",
pages = "285--293",
journal = "Marketing Science",
issn = "0732-2399",
publisher = "INFORMS Inst.for Operations Res.and the Management Sciences",
number = "2",

}

Dynamic models incorporating individual heterogeneity : Utility evolution in conjoint analysis. / Liechty, John C.; Fong, Duncan; Desarbo, Wayne.

In: Marketing Science, Vol. 24, No. 2, 01.03.2005, p. 285-293.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Dynamic models incorporating individual heterogeneity

T2 - Utility evolution in conjoint analysis

AU - Liechty, John C.

AU - Fong, Duncan

AU - Desarbo, Wayne

PY - 2005/3/1

Y1 - 2005/3/1

N2 - It has been shown in the behavioral decision making, marketing research, and psychometric literature that the structure underlying preferences can change during the administration of repeated measurements (e.g., conjoint analysis) and data collection because of effects from learning, fatigue, boredom, and so on. In this research note, we propose a new class of hierarchical dynamic Bayesian models for capturing such dynamic effects in conjoint applications, which extend the standard hierarchical Bayesian random effects and existing dynamic Bayesian models by allowing for individual-level heterogeneity around an aggregate dynamic trend. Using simulated conjoint data, we explore the performance of these new dynamic models, incorporating individual-level heterogeneity across a number of possible types of dynamic effects, and demonstrate the derived benefits versus static models. In addition, we introduce the idea of an unbiased dynamic estimate, and demonstrate that using a counterbalanced design is important from an estimation perspective when parameter dynamics are present.

AB - It has been shown in the behavioral decision making, marketing research, and psychometric literature that the structure underlying preferences can change during the administration of repeated measurements (e.g., conjoint analysis) and data collection because of effects from learning, fatigue, boredom, and so on. In this research note, we propose a new class of hierarchical dynamic Bayesian models for capturing such dynamic effects in conjoint applications, which extend the standard hierarchical Bayesian random effects and existing dynamic Bayesian models by allowing for individual-level heterogeneity around an aggregate dynamic trend. Using simulated conjoint data, we explore the performance of these new dynamic models, incorporating individual-level heterogeneity across a number of possible types of dynamic effects, and demonstrate the derived benefits versus static models. In addition, we introduce the idea of an unbiased dynamic estimate, and demonstrate that using a counterbalanced design is important from an estimation perspective when parameter dynamics are present.

UR - http://www.scopus.com/inward/record.url?scp=20444473470&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20444473470&partnerID=8YFLogxK

U2 - 10.1287/mksc.1040.0088

DO - 10.1287/mksc.1040.0088

M3 - Article

VL - 24

SP - 285

EP - 293

JO - Marketing Science

JF - Marketing Science

SN - 0732-2399

IS - 2

ER -