Accounting for J-shape distributions to explain customer ratings
(A2023-114340)

AUTHORS

Nadine Schröder, WU Wien; Thomas Reutterer, WU Vienna University of Economics and Business; Konstantin Kremslehner, Department of Marketing / Vienna University of Economics and Business Administration

ABSTRACT

In many customer feedback scenarios respondents often report that they were highly satisfied with a product or service. This phenomenon has gained a lot of attention in the field of product reviews and is known by the J-shape distribution of ratings. The distributional characteristics of these rating data pose issues when the task is to model the relationship with other (potentially) explanatory variables as we do in our study. Instead to look at the actual rating, we propose a model that explains the probability of a favorable rating and compare it to an alternative model (used in previous research). We evaluate the performance of the models based on model selection criteria and find that focusing on the probability improves model fit. As coefficients vary in terms of significance across the models, different recommendations and conclusions for managerial decision making would result which makes the right model choice important. We illustrate the case for self-reported customer feedback in an online review context.