The focus of this paper is a re-sampling technique, namely the bootstrap, for assessing the reliability of combining data from a large number of individuals in a conjoint analysis procedure. The issue of aggregation of preferences is a crucial one in large-scaled surveys where it is often used to simplify the analyses and obtain results in a more concise and therefore manageable form. The bootstrapping technique is applied to two large sets of data collected by an insurance firm. Results strengthen the relevance of this technique. The computer program, using the SAS package, is presented.
The Price Audit is a micro-analytic method for testing the effect of a change in price on a products market standing. Simple in theory and economical to put into practice, the method generates an impressive amount of data that enables one to develop a multi-faceted view of how a products position in the market ( in terms of how it is perceived and evaluated, its market share, and the consumer segments from which it draws) is influenced by its price and how that position might change given a change in the products price or in that of one of its competitors. In what follows, we will first discuss the theoretical and methodological bases of the Price Audit and describe each of the calculations of which it consists. We will then illustrate the method with an overview of the results from a recent application, and then close with a brief discussion of these findings and of various issues that arise in their interpretation.
This paper discusses the measurement of perception and motivation, concentrating on two techniques used for this measurement task. Factor analysis has traditionally been used for the measurement of perception and motivation, while correspondence analysis has become increasingly popular in recent years. This paper contrasts the implications of using these techniques, using case studies to illustrate their strengths and weaknesses. In addition to the discussion on the measurement of perception and motivation, the paper addresses the problem of identification of submarkets within markets. The identification of these sub-markets and the analytical implications thereof are fully discussed, again using correspondence analysis and factor analysis to support the discussion.
There has been growing interest in recent years in the tracking of advertising effects on sales and brand awareness through the use of econometric techniques. Typically, however, these approaches using Koyck transformations suffer from the problem of autocorrelation within the data. This paper presents an alternative approach, commencing with the removal of systematic variations in the dependent variable through the use of ARIMA modelling techniques. The combined approach is termed ADTRAC. This paper presents three examples of ADTRAC modelling for a major national UK retailer.
The paper is intended to explain the basic principles of TESI and to illustrate its scope of application and information. It will also be shown how test market simulation can be used to analyse existing markets, uncover the competitive relations between the brands and detect the determinant factors of buying behaviour. This information is also important for the marketing of existing brands and can support the development of more efficient marketing strategies.
This paper is concerned with promotional pricing. It is studied in the context of a major consumer products category in the Canadian Market using electronic diary data. Price effects on several brands are shown. One brand is analysed in greater detail in order to show the full economic consequences of promotions.
The paper presents the case of a Dutch theatre facing the problem of revising the range of seat categories, and of setting the ticket prices on the basis of sales records and of consumer demand. Demand was analysed through interviews aiming at finding out consumer perceptions of seats characteristics. "Visibility", "acoustics", "sitting comfort" and "surrounding space" were identified as the main attributes. Their j.n.d.'s were analysed according to Weber-Fechner law. As a result of the study, the number of seat categories was reduced from 9 to 3, and prices were rearranged according to research results and company policy.
This paper deals with short-term forecasting of market shares using market share models. The predictive power of market share models is a subject that has received considerable attention in marketing literature. However, hardly any attention has been paid to the question of how the values of the marketing instruments of competitors can be predicted. This is remarkable since these values constitute the input variables for the market share model. In this paper we will investigate the sensitivity of predicted market shares to different assumptions with respect to competitive behaviour.
In this paper the current version of a pre-test market system will be described which is designed to perform a comprehensive analysis of individual choice, perception and preference data, offers different ways to compute market share estimates, takes into consideration cannibalisation and draw effects in the underlying product class, allows for a segmentation based identification of mostly preferred perceptual space locations with respect to the choice alternatives under study and provides different options for evaluating the given data by means of e.g. internal, external, deterministic, probabilistic, uni- and/or multidimensional analyses. Some features of the used methodology will be illustrated on the basis of a case study recently evaluated in collaboration with a market research institute.
A micro-behavioral marketing model provides the conceptual framework to explain free choice decision making among consumers who purchase our products or services. Since it is a micro model, it portrays the decision making of each individual respondent, one at a time. The underlying structure of the model is a highly simplified representation of the extremely complicated cognitive processes which actually take place when a consumer decides to choose or not choose a particular product or service. The simplifying assumption is that we are "creatures of satisfaction." We tend to make decisions, within acceptable economic and social constraints, which favour the things we like the most and derive the most satisfaction from possessing.
The purpose of this contribution to our seminar on modelling is to make two points: 1. There is usually little point in modelling something if we do not know what it is; 2. Developing the required empirically-based generalisations in marketing is both possible and essential. To illustrate, we summarise an experimental study on pricing carried out in the UK in 1986. Our aim was to establish whether the sales response to a given price change would generalise.
This paper summaries the authors' experience in estimating the sales impact of product quality improvements, made to new products. The paper describes the manner in which a particular forecasting technique takes account of product evaluation in its estimation process, and clarifies the specific components of sales affected by product quality. Case history material is shown to demonstrate the sales impact of product improvement. Four specific points are highlighted. First, the importance of high product quality in launching new brands. Second, the impact on sales that variance in product quality can have. Third, that the sales impact generated by product improvements can be estimated pre-launch. Fourth, that pre-test market systems can, and should, be used as diagnostic tools to evaluate product change.