Looking for Loss Aversion in Scanner Panel Data: The Confounding Effect of Price-Response Heterogeneity

Recent work in marketing has drawn on behavioral decision theory to advance the notion that consumers evaluate attributes not just in absolute terms, but as deviations from a reference point. Using scanner panel data, choice modelers have examined the presence "reference effects" in consumer response to attributes such as price. In particular, the theory and empirical findings suggest that when a consumer encounters a price above his or her established reference point (a "loss"), the response is greater than for a price below the reference point (a "gain"). It is our contention in this paper that the measurement of loss aversion may be confounded by the presence of consumer heterogeneity in price responsiveness. Our reasoning is that a more price-responsive household (whose reference point involves a lower price level) faces a larger proportion of "losses" than does a less price responsive household, ceteris paribus. As a result, any cross-sectional estimate of loss aversion will be biased upward. We test our assertion using scanner panel data on refrigerated orange juice. Using two different approaches to account for price response heterogeneity (a segment-level mixture model and household-level Bayesian estimation), we find substantially lower (if not altogether negligible) estimates of loss aversion.