Knowledge that Transforms

The authors examine the rescheduling of television programs to maximize the total ratings for one network across a week. The key idea is to design a choice experiment in which television programs are rescheduled and presented to respondents. Respondents read these program schedules (much like the regular TV Guide listings) and give their preferences, including not watching any of the listed programs. Because there are potentially billions of possible schedules, the authors give a procedure for designing a fractional factorial experiment that can accommodate both programs of varying length and constraints on eligible program times. The authors also develop a latent class multinomial logit model for modeling program preferences and present a validation of our experimental procedure and the model. They also present an empirical test of the procedure in which they use the model to predict ratings for all the possible program schedules, not just those constituting the choice sets. In this example, the optimum schedule increases the predicted total weekly ratings during prime time by 18% for a network. The projected increase in total weekly ratings is achieved without the network needing to purchase any new programs; all it needs to do is reschedule eight programs in its existing prime-time lineup.

Marketing research studies pertaining to market segmentation, competitive market structure, and product/service positioning often involve the collection of multiple batteries of measurements from the same set of respondents (e.g., preferences, attribute ratings, demographics, proximity judgments). Various multidimensional scaling (MDS) and spatial methods have been used in the analysis of these variable batteries separately but not much effort has been expended in attempting to relate the individually derived spatial structures. The authors propose a new latent structure MDS procedure that is devised to represent jointly the structure in multiple batteries (preferences, proximities, and brand attribute ratings) of variables collected across the same set of respondents. The authors present the technical structure of the proposed maximum likelihood–based model and conceptually compare it with other related spatial MDS models. The authors present an illustration of the procedure with respect to the analysis of published proximity, preference, and brand ratings data collected from consumers who evaluated ten brands of soft drinks.

The authors explore the effect of a form of question context on responses to a computer-mediated marketing research survey. As an increasing proportion of marketing research is conducted through computer interfaces, the pool of potential context effects is rapidly expanding. The authors conduct an experiment using a multi-item scale that consists of five dimensions and manipulate three such context effects: explicit item labeling, item presentation (alone/grouped), and subscale items presented contiguously or not. In a refined analysis of variance, the authors use a special one-dimensional case of the spatial and attribute-based distance metric proposed by Hoch, Bradlow, and Wansink (1999) to explain subscale variance, replacing the indicator variable for clustering used in a standard analysis of variance. This metric provides a scalar measure of how much variation exists in the order of presentation of items within a subscale (the subscale distance). This analysis indicates a significant decrease in subscale variance (increased reliability) with decreasing sub-scale distance but no-longer-significant effects due to labeling and grouping. The authors discuss implications of their findings for researchers conducting surveys in computer-mediated environments.

The authors present a framework that enables researchers to differentiate better among a wide array of hedonic products. Specifically, the authors define and discuss characteristics of hedonic portfolio products and offer a joint segmentation model that is appropriate for understanding the sales dynamics of this class of products. The model offered in this article can accommodate a large degree of product heterogeneity through product clusters and model covariates. The basic premise is that several generic consumer segments exist and remain fixed across all albums, and each album (or each cluster of similar albums) can be viewed as drawing different proportions from each of these underlying segments. The authors also allow explanatory variables to have a differential impact on both components of the model—that is, accelerating purchase rates within a consumer segment and changing the proportions drawn from each consumer segment by each product cluster—thereby expanding or contracting the potential market size. The authors apply this model to music compact disc sales for 20 different albums and discuss the different effects of radio airplay and holiday buying on sales for a sample in the music industry.

Despite the importance of product line management as a competitive tool, empirical research addressing the determinants of firm product line decisions is sparse. In this article, the authors propose and empirically estimate a descriptive model of firm product line decisions in the personal computer industry over the period 1981-92. The model incorporates the firm's initial choice of the direction of a product line change (i.e., the product line can be expanded, contracted, or maintained) and the conditional choice related to the magnitude of any product line change (i.e., how many products to introduce or withdraw). The authors show that there are important substantive insights to be gained by analyzing the product line decision in this fashion. In the personal computer industry, for example, firms expand their product lines when industry barriers are low or market opportunities are perceived to exist. High market share firms aggressively expand their product lines, as do firms with relatively high prices or short product lines. In general, the results highlight the various internal and external factors that influence firms' management of their product lines.

The authors examine consumer inferences about product attributes that are unobservable at the time of the decision. Extant research predicts that in the absence of an explicit correlation between product attributes, consumers will infer that the brand that is superior on the observable attributes is also superior on the unobservable attributes. The authors propose an alternative inference strategy that makes the counterintuitive prediction that the apparently superior brand is inferior on the unobservable attributes. The authors refer to these inferences as “compensatory inferences” and assert that they are associated with consumers' intuitive theories about the competitive nature of a market. In a series of four experiments, the authors examine the occurrence of compensatory inferences and compare them with other inference strategies.