No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
An Investigation of Brand Choice Processes
... If one assumes that p t-k can only take r different values ranging from m 1 to m , equation 13 can be written for a particular value, ~i z. m 1 , as: i.e., Prob(h,lpt-k = m 1 ) for the LLM-parameter values &, ~. and X. can be computed directly by use of the definition of the LLM. This computation can be done for all r possible values of P t-k· Suppose no prior information so that all values 'Because the dependent variables are probabilities, generalized least squares could be used instead of ordinary least squares. ...
... The numbers of households of which the brand choice data were used are 613, 666, and 850 for beer, fopro, and margarine, respectively. More details about the data can be found in [13]. For each product the biggest brand in the market was called brand l. ...
... It was used extensively in [IO] , and other authors have used the method subsequently [e.g. l, 9,11,13]. Carman [3] described an estimation method which is essentially a regression procedure, but very different from the least squares method presented here. ...
The author presents a new method for estimating the parameters of the linear learning model. The procedure, essentially a least squares method, is easy to carry out and avoids certain difficulties of earlier estimation procedures. Applications to three different data sets are reported, as well as results from a goodness-of-fit test. A simulation study was carried out to validate the method. The outcomes are compared with those obtained from the minimum chi square estimation method. The results of the new method appear to be satisfactory.
... Another approach taken by several researchers to assess the order of the brand-choice process was to test sequences of purchases by individual households using, say, a runs test (e.g., Frank, 1962;Massy, 1966;Wierenga, 1974;Bass et al., 1984). While the idea of such an approach is attractive, the need for long sequences of brand choices for each household is a problem. ...
... To illustrate, one natural source of variance is in the set of altematives households actively consider at the time of choice. Though aggregate-share benchmarks assume that all alternatives face the same set of considered alternatives on each choice occasion, empirical evidence suggests that such assumptions of homogeneity are dubious (see, e.g., Silk and Urban 1978;Wierenga 1974). Specifically, the set of alternatives considered at the time of choice could vary across households because of such things as different accessibilities to products (not all JOURNAL OF MARKETING RESEARCH, FEBRUARY 1994 households can utilize the same channels of distribution), differences in product awareness, and differences in perceptions of options that are dominated in the market by other alternatives (Narayana and Markin 1975). ...
In assessing the performance of a choice model, we have to answer the question, “Compared with what?” Analyses of consumer brand choice data historically have measured fit by comparing a model's performance with that of a naive model that assumes a household's choice probability on each occasion equals the aggregate market share of each brand. The authors suggest that this benchmark could form an overly naive point of reference in assessing the fit of a choice model calibrated on scanner-panel data, or any repeated-measures analysis of choice. They propose that fairer benchmarks for discrete choice models in marketing should incorporate heterogeneity in consumer choice probabilities, evidence for which is by now well documented in the marketing literature. They use simulated data to compare the performance of parametric and nonparametric benchmark models, which allow for heterogeneity in consumer choice probabilities, with the performance of the aggregate share-based benchmark model, which assumes consumers are homogeneous in their choice probabilities. They also assess the performance of two previously published consumer behavior models against the proposed fairer benchmark models that allow for heterogeneity in consumer choice probabilities. They find that one provides a significantly better fit than their more conservative benchmark models and the other performs less favorably.
... The ranges observed in this quantity for these three product categories were 1-12, 1-8, and 1-11, respectively. Wierenga [70,Chapter 6) investigated some related phenomena using purchase diary data from a panel of 2,000 Dutch households. He found that although a total of 29 different brands accounted for 85 % of the total volume of margarine purchased, the mean number of brands purchased per household over a two-year period was only 4.26. ...
The substantial failure rate of new packaged goods in test markets has stimulated firms to seek improved methods of pre-test-market evaluation. A set of measurement procedures and models designed to produce estimates of the sales potential of a new packaged good before test marketing is presented. A case application of the system also is discussed.
... Marketing researchers commonly use two models to analyze consumer panel data: (1) the negative binomial distribution (NBD) model (Ehrenberg 1972) and (2) the beta-binomial distribution (BBD) model (Massy, Montgomery, and Morrison 1970;Wierenga 1974). ...
Consumer panel data are typically available for a fixed duration of time (say, a year) during which buyers invariably make different numbers of purchases in the product class. The author describes a method for obtaining maximum likelihood estimates of zero-order models from panel data containing different numbers of purchase records per household. Empirical data are presented to illustrate the application of the estimation method.
... Another approach taken by several researchers to assess the order of the brand-choice process was to test sequences of purchases by individual households using, say, a runs test (e.g., Frank, 1962;Massy, 1966;Wierenga, 1974;Bass et al., 1984). While the idea of such an approach is attractive, the need for long sequences of brand choices for each household is a problem. ...
... Stochastic consumer models such as Markov processes and linear learning models have been applied to brand choice for agricultural products (e.g. Wierenga, 1974;van Tilburg, 1984). ...
The thesis of this paper is that in agricultural marketing theory the basic approach to marketing problems should be the 'marketing management' approach. In order to substantiate this thesis, the developments in agricultural marketing and general marketing theory are concisely reviewed. The elaboration of marketing management in agricultural marketing is discussed in relation to the properties of the marketing environment and to the marketing capacities of an agricultural marketing system. (Abstract retrieved from CAB Abstracts by CABI’s permission)
... Linear specifications for the state-dependence partial utilities do not allow for a behavior where both inertia and variety seeking may coexist within the individual for the same attribute. However, some empirical evidence consistent with a mixed behavior was originally reported by Wierenga (1974), who observed that consumers tend to fluctuate between repeat purchasing and brand-switching behavior for frequently purchased products. From now on, we refer to this mixture of inertia and variety seeking as hybrid behavior. ...
This paper presents a dynamic choice model in the attribute space considering rational consumers. The model presents a stationary consumption pattern that can be inertial, where the consumer only buys one product, or a varietyseeking one, where the consumer shifts among varied products. Under the hybrid utility assumption, the consumer behaves inertially among the unfamiliar brands for several periods, eventually switching to a varietyseeking behavior when the stationary levels are approached. An empirical illustration with myopic agents is run using scanner databases for three different product categories: fabric softener, saltine cracker, and catsup. Nonlinear specifications provide the best fit of the data, as hybrid functional forms are found in all the products. The resullts confirm the gradual trend to seek variety as the level of familiarity with the purchased items increases.
... Many researchers have proposed stochastic models for analyzing the multibrand purchasing behavior of households for frequently purchased products (e.g., Ehrenberg, 1972;Bass, 1974;Wierenga, 1974;Bass, Jeuland and Wright, 1976;Goodhardt, Ehrenberg and Chatfield, 1984). A key element in the development of such models has been the extensive use of panel data, a longitudinal history of household purchases. ...
In a recent study, Kahn, Morrison and Wright showed that for exponentially distributed interpurchase times (of individuals), the household choice process approaches a zero-order process as the number of individuals in the household increases, even though the purchasing behavior of each individual is first order. We show that their result holds for any arbitrary interpurchase-time distribution that has a density over some interval. Thus, additional support is provided for their conclusion that the empirically observed zero-order choice behavior at the household level may not convey much information about individuals' choice behavior. We also derive a general formula that determines exactly the degree of dependence between two successive household purchases for any given family size and (well-behaved) interpurchase-time distribution.
A measure of temporal variety is developed and is used as a dependent variable in an investigation of the variability in individual purchases from three product classes. Predictor variables are used to characterize individuals who exhibit higher versus lower levels of purchase variability and to classify a holdout sample.
Marketing management is provided with a fundamental logic to guide strategic and operational planning. One descriptive element is a model of the customer. Other descriptive elements feed upon this customer model for informational input in a dynamic process over the life cycle. The five key functions of each company adapt to these changes and to each other in a series of management process innovations. The financial criteria of maximizing shareholder wealth and maximizing viewed as an ideal are the prescriptive elements.
Except for some food production for private consumption, most food products are purchased in the market. This is the domain of food marketing. Broadly speaking, marketing as a scientific discipline is concerned with the exchange processes that occur between a firm or organization that offers products or services to the market, and the target group(s) of potential buyers in its environment. Marketing focuses on policies and strategies which firms adopt to satisfy the needs and wants of the target groups more effectively and efficiently than competitors do. The basic assumption is that the organization that can do so most effectively and efficiently will be most successful in achieving its organizational objectives.
In the present chapter, we briefly discuss how knowledge generation in marketing can be accomplished. In particular, we argue that generalizations offered by meta-analyses are very useful for managers in their decision making. To support this argument, we perform an empirical study on subjective estimations of price elasticities, advertising elasticities, and price promotion elasticities, showing that actual and future managers (i.e., master and PhD students) usually underestimate the effects of price changes, overestimate the impact of advertising, and heavily underestimate that of price promotions. We also demonstrate that subjective estimations improve after being confronted with the outcomes of meta-analyses. © 2012 Gabler Verlag | Springer Fachmedien Wiesbaden. All rights reserved.
De mogelijkheid tot de ontwikkeling van interdisciplinaire modellen waarmee met behulp van een combinatie van elementen uit economie en psychologie (en eventueel sociologie) een beter inzicht kan worden verkregen in de achtergronden van het consumentengedrag
If utility (net of price) varies by consumption occasion, the consideration set of a rational consumer will represent trade-offs between decision costs and the incremental benefits of choosing from a larger set of brands. If evaluating a brand decreases bias and uncertainty in perceived utility, the decision to evaluate a brand for inclusion in a consideration set is different from the decision to consider an evaluated brand. The decision to consumer is, in turn, different from the decision to consider. This article provides analytical expressions for these decision criteria and presents four aggregate implications of the model: (1) distributions of consideration set sizes, (2) order-of-entry penalties, (3) dynamic advertising response, and (4) competitive promotion intensity. Copyright 1990 by the University of Chicago.
ResearchGate has not been able to resolve any references for this publication.