No abstract

No abstract

Whether, what and how much to buy are central decisions in consumer goods markets. Marketing research commonly uses a sequential approach where quantity decision is conditional on purchase incidence and brand choice (e.g., Ailawadi et al. in J Mark Res 44:450-467, 2007). This approach assumes separability between decisions and suffers from selectivity bias. The bias can be overcome by explicitly controlling for it (e.g., Zhang et al. in Rev Mark Sci 3(1), 2005) or by using one unifying utility function, a method considered ''state of the art in analyzing purchase behavior in a single product category'' (e.g., Song and Chintagunta in J Mark Res 44(4): [595][596][597][598][599][600][601][602][603][604][605][606][607][608][609][610][611][612] 2007). However, this latter method puts restrictive assumptions on the influence of prices on choices, which may affect managerial implications derived from the model results. This study investigates the effect of selectivity bias by comparing the sequential approach-with and without explicitly controlling for endogeneity bias-to the unifying utility function approach. Based on household panel data from three categories, we illustrate the extent to which managerial implications from these frameworks differ. We show that the superiority of one framework versus the other depends on the specific category and its characteristics. The managerial implications of using the ''wrong'' framework are demonstrated by conducting two simulation studies; these show that price elasticities substantially deviate across frameworks.

This research studies the propensity of individuals to violate implications of expected utility maximization in allocating retirement savings within a compulsory de…ned contribution retirement plan. The paper develops the implications and describes the construction and administration of a discrete choice experiment to almost 1200 members of Australia's mandatory retirement savings scheme. The experiment …nds overall rates of violation of roughly 25%, and substantial variation in rates, depending on the presentation of investment risk and the characteristics of the participants.Presentations based on frequency of returns below or above a threshold generate more violations than do presentations based on the probability of returns below or above thresholds. Individuals with low numeracy skills, assessed as part of the experiment, are several times more likely to violate implications of the conventional expected utility model than those with high numeracy skills. Older individuals are substantially less likely to violate these restrictions, when risk is presented in terms of event frequency, than are younger individuals. The results pose signi…cant questions for public policy, in particular compulsory de…ned contribution retirement schemes, where the future welfare of participants in these schemes depends on quantitative decision-making skills that a signi…cant number of them do not possess.2

No abstract