Omitted Budget Constraint Bias and Implications for Competitive Pricing
Journal of Marketing Research, forthcoming
Posted: 30 Sep 2017 Last revised: 13 Dec 2022
Date Written: November 29, 2022
Abstract
Standard Choice-Based Conjoint (CBC) models often ignore or insufficiently approximate consumers’ budget constraints, despite the prominent role of budget constraints in
economic theory. The authors offer a theoretically motivated improvement to the CBC
model that is especially appropriate for high-ticket durable goods and develop a Bayesian
method for the inference of unobserved budget constraints. The proposed method leverages respondents’ stated budget constraints that suffer from measurement error and respondents’ financial demographic variables as additional information to reduce the dependency
on functional form assumptions in the estimation. The authors show that accounting for
budget constraints substantially increases model fit and the accuracy of competitive pricing in an industry-grade discrete-choice experiment on consumer preferences for high-end
laptops. The proposed model performs better than the canonical linear price benchmark
model, which is not flexible enough to approximate budget constraints. In theory, more
flexible utility specifications, such as the non-linear dummy price model, can approximate
consumers’ budget constraints. However, they perform poorly when only finite data are
available. The authors conclude that applied researchers in industry and academia will
benefit from having a better tool for estimating budgets in high-ticket categories.
Keywords: budget restrictions, demand estimation, competitive pricing, choice-based conjoint, Bayesian inference
Suggested Citation: Suggested Citation