The Spatial Representation of Market Information
Marketing Science, Vol. 20, No. 4, pp. 426-441, 2001
Posted: 13 Jun 2016
Date Written: 2001
To be used effectively, market knowledge and information must be structured and represented in ways that are parsimonious and conducive to efficient managerial decision making. This manuscript proposes a new latent structure spatial model for the representation of market information that meets this requirement. When applied to a priori defined (e.g., socioeconomic) segments, our proposed methodology provides a new way to display marketing data parsimoniously via dimension reduction through a factor-analytic specification. In post hoc studies, we simultaneously derive market segments from the data and represent the structure of market information within each of the unobserved, derived groups/segments. We summarize all relevant information concerning derived market segments via a series of maps that prove conducive to the quick and accurate dissemination of customer and competitor market information. The associations between the variables are captured in a reduced space, where each variable is represented by a vector that emanates from the origin and terminates on a hypersphere of unit (the vector length is arbitrary) radius (e.g., a unit circle in a two-dimensional space). The angles between the variable vectors capture the correlation structure in the reduced space. The method is very general and can be utilized to identify latent structures in a wide range of marketing applications. We present an actual commercial marketing application involving the (normalized) prescription shares (of specialists) of ethical drugs to demonstrate the effectiveness of representing market information in this manner and to reveal the advantage of the proposed methodology over a more general finite mixture-based method. The proposed methodology derives three segments that tend to group specialists with respect to the stage of adoption of innovation in this therapeutic category. The specialists in the first group appear to be laggards because they prescribe more of the older class of brands. However, they also have a higher-than-average preference for a newer and somewhat cheaper brand. This suggests that some of the specialists belonging to this segment may be price sensitive, while others may exhibit a slower adoption cycle, replacing the older class with the newer brands, and thus, skip one stage in the cycle of innovation. The specialists in the second segment are heavy users of the newer class of brands but are not particularly fast to adopt the latest brands. Finally, the last segment clearly consists of innovators. Traditionally, pharmaceutical marketers have viewed specialists in one of two extremes—all specialists are the same (i.e., the market has only one segment) or all specialists are very different (i.e., the market consists of 10,000 segments of one physician each). Not surprisingly, this analysis suggests a more moderate perspective: specialists adopt new products at different rates.
Keywords: Spatial Models, Market Segmentation, Latent Structure Analysis, Maximum Likelihood Estimation, Ethical Drugs
Suggested Citation: Suggested Citation