It is very difficult for the headquarters of multinational corporations, for offshore firms without local branches, or for market research institutes without local associates, to evaluate the market research undertaken in the Latin American region, i.e., to know what is done and how it is done. This paper seeks to respond to some of the questions which are often posed by such foreign organisations interested in exploring Latin American markets. The first part is devoted to a reflection on how certain local conditions have an influence upon the way market research is conducted. The second part brings forth examples of complex studies, presenting three cases in which multivariate techniques were used. The paper ends with a reflection on the need for a greater local development of techniques adapted to the local milieu.
This paper presents a quantitative marketing research survey through the use of multivariate techniques to address several pre-launch issues of a new product. The main emphasis in the analysis is the use of the conjoint model to determine the actual market share potential of a new product against a defined market. The survey addressed other marketing issues such as product awareness, usage, psychographic segmentation, promotional emphasis, pricing and positioning. After identifying each potential market segment, the use of the conjoint model produced a market estimate that was significantly accurate to the actual market share 12 months after launch.
Most multivariate techniques require an immense number of calculations which, whilst not beyond the resources of clerks and adding machines, are more quickly and economically carried out by computer. It is not my intention in this chapter to dwell at large on the theoretical properties underlying the basis of the varying types of multivariate procedures. The inclusion of statistical and mathematical formulae will be kept to a minimum. References to the appropriate literature will be quoted for the interested reader to pursue at his leisure. The main aim is to present a somewhat simplified overview of a rather complex subject matter in as non mathematical a manner as possible.
This paper describes the experimental application to the identification of bank images of a technique previously used to differentiate between consumer goods such as lagers and perfumes where differences were subtle. The approach is based on the use of a battery of adjectives and adjectival phrases which the respondent uses to describe the "personality" of the institution. The initial step is the development of the battery of words and phrases. This is divided into two phases, the 'trigger' sessions, which are used to generate a comprehensive (and too long) list, and the 'charade* sessions which are used to reduce the list to manageable proportions by determining those words or phrases which are the best identifiers of the institutions. The analysis is also critical in order to distill the essential discriminators from the mass of data. A range of multi-variate techniques were used to discriminate between the banks and describe their personalities.
In November 1978 a new tabloid newspaper was launched in the Midlands and Northern areas of England. It was positioned directly against existing popular newspapers. Marplan, on behalf of The Sun, monitored its launch in order to predict its sales level and to identify its editorial strengths and weaknesses. This paper describes the sales success achieved by that newspaper: evaluated against its published targets. Most of the paper, however, deals with the level of editorial success achieved: and how this compares with the editorial ratings given to existing popular newspapers. As a bi-product of this study much data of value emerges on the editorial requirements of readers of mass circulation daily newspapers. The paper describes the techniques used - and the results obtained. Finally the paper describes a multivariate approach to classifying people in terms of their requirements from popular newspapers. This approach offers significant opportunities for the accurate identification of "what leads people to read popular newspapers".
This paper is concerned with perspectives on the use of multivariate techniques in marketing. The marketing concept has taught us to define markets and products in terms of human needs. This has fostered two fundamental segmentation stratagems: brand-benefit segmentation and consumer-benefit segmentation. In addition to benefit segmentation, the marketing concept has stimulated research on basic human needs. This latter development is frequently referred to as psychographic research. In spite of massive efforts at the level of benefits and psychographics, segmentation research has frequently failed to live up to expectations in predicting marketing behavior. The paper introduces the concept of morphological segmentation to aid in the combining of the benefit and psychographic traditions. In addition, morphological segmentation addresses some of the theoretical and practical limitations of market predictability.
Cluster analysis has become a very popular multivariate method in market research during the last five to seven years. Its wide propagation does this method probably owe to the simplicity of its basic ideas. But contrary to this simplicity stand some special dangers which are connected with the application of cluster analysis. These crucial points are discussed in this paper, rules are developed for a meaningful use and some methodical questions which are still open will be pointed out.
The purpose of this communication is to analyse the role and the function of statistical methods in the development of Marketing Information Systems. This analysis will be conducted at two main levels: 1. Integration of the bank of statistical methods in the system; 2. Storage of reduced data.
In this report a new multivariant model is presented. In the first section a use-oriented systematic is developed. Within this systematic the multivariant technique, at present in vogue in practical research, is arranged. The new technique: Partial Typology, is identified as lying within the field of Cluster Analysis models. The systematic approach of the method identifies the differences in principle between this technique and other multivariant techniques. In contrast to other techniques two interdependent fields of variables are used to build the clusters. In the second section of the report the method of Partial Typology is presented in detail by using a case study from the field of regional research. The relationship between population mobility and community structure is investigated over six periods. The results of the investigation show the particular advantages and knowledge to be obtained from using Partial Typology. In section three the procedural realization and suitable criteria for optimization are described.
In this report a new multivariant model is presented. In the first section a use-oriented systematic is developed. Within this systematic the multivariant technique, at present in vogue in practical research, is arranged. The new technique: Partial Typology, is identified as lying within the field of Cluster Analysis models. The systematic approach of the method identifies the differences in principle between this technique and other multivariant techniques. In contrast to other techniques two interdependent fields of variables are used to build the clusters. In the second section of the report the method of Partial Typology is presented in detail by using a case study from the field of regional research. The relationship between population mobility and community structure is investigated over six periods. The results of the investigation show the particular advantages and knowledge to be obtained from using Partial Typology. In section three the procedural realization and suitable criteria for optimization are described.
After six years of utilization of multivariate techniques, we discover that these techniques have brought us along to conceive studies of a more complex structure as well as more clear in their basic assumptions. In this paper, we attempt to analyse the mechanism of that enrichment which appears to be located on different levels both logical and chronological.