No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Industrial buying behavior: Aviation fuel contracts
Abstract
Contracts for oil companies to supply airlines with aviation fuel at different European airports follow regular patterns. For example, the loyalty of airlines tends to be highly divided among different oil companies, and there is no sign of any marked segmentation. The patterns resemble those found for fast-moving consumer goods (fmcg) markets and the same theoretical Dirichlet model holds. Underlying analogies with fmcg markets and managerial implications are drawn out.
... In addition, the NBD-Dirichlet literature has primarily been concerned with fast moving consumer goods with few applications in organisational purchasing behaviour (Uncles & Ehrenberg, 1990;Bowman & Lele-Pingle, 1997;Pickford & Goodhardt, 2000). Although concerned with buying behaviour in organisations, these studies have all featured independent organisations that are not operating within the constraints of a collaborative purchasing framework. ...
... Sharp et al. (2002) note the distinction between repertoire markets, where consumers satisfy their requirements from a repertoire of brands, and subscription markets where high levels of source loyalty are the norm. The few empirical studies carried out in organisational markets have shown similar patterns of repeat purchasing, mainly in fast moving industrial goods and services such as aviation fuel (Uncles & Ehrenberg, 1990), ready mixed cement (Pickford & Goodhardt, 2000) and financial exchange services (Bowman & Lele-Pingle, 1997). Uncles & Ehrenberg (1990) analysed a selection of aviation fuel contracts held by airlines across different locations (airports). ...
... The few empirical studies carried out in organisational markets have shown similar patterns of repeat purchasing, mainly in fast moving industrial goods and services such as aviation fuel (Uncles & Ehrenberg, 1990), ready mixed cement (Pickford & Goodhardt, 2000) and financial exchange services (Bowman & Lele-Pingle, 1997). Uncles & Ehrenberg (1990) analysed a selection of aviation fuel contracts held by airlines across different locations (airports). The analysis was static in that it only considered the contracts with a particular fuel supplier at a particular point in time and did not take into account any repeat purchasing. ...
... We also highlight the differences between these previous studies and the empirical analyses reported in this paper. Uncles and Ehrenberg (1990) analyzed a selection of aviation fuel contracts awarded by airlines across different locations (airports). The analysis considered the contracts between airlines and their fuel suppliers at a particular point in time and did not take into account any renegotiation of these contracts. ...
... The relevant population of buyers is defined by the scope of the analysis and may be bounded by the analyst on a regional basis (e.g. the concrete analysis by Pickford & Goodhardt, 2000), or by an industry structure determined by the activities of the buying organization (e.g. airlines Uncles & Ehrenberg, 1990), prescribing physicians (Stern, 1994). The measures used to parameterize the Dirichlet model are the market share and the penetration, both of which require a "closed" definition of the market. ...
... Aviation fuel (Uncles & Ehrenberg, 1990) No Partial a 1 year Stationary ...
It is increasingly recognized that progress can be made in the development of integrated theory for understanding, explaining and better predicting key aspects of buyer–seller relationships and industrial networks by drawing upon non-traditional research perspectives and domains. One such non-traditional research perspective is stochastic modeling which has shown that large scale regularities emerge from the individual interactions between idiosyncratic actors. When these macroscopic patterns repeat across a wide range of firms, industries and business types this commonality suggests directions for further research which we pursue through a differentiated replication of the Dirichlet stochastic model. We demonstrate predictable behavioral patterns of purchase and loyalty in two distinct industrial markets for components used in critical surgical procedures. This differentiated replication supports the argument for the use of stochastic modeling techniques in industrial marketing management, not only as a management tool but also as a lens to inform and focus research towards integrated theories of the evolution of market structure and network relationships.
... The NBD, introduced into the marketing literature by Andrew Ehrenberg over sixty years ago (Ehrenberg, 1959), is an appropriate model with which to examine questions involving brand purchases and related metrics over several years, being both highly generalised and parsimonious in use. Its applications have been extended from consumer packaged goods brand and category buying (Chatfield et al., 1966;Dawes, 2014;Ehrenberg, 1988;Ludwichowska et al., 2017;Uncles et al., 2010), to the use of gambling products (Lam & Mizerski, 2009;Mizerski et al., 2004), consumption of mobile phone services (Lee et al., 2011), healthy behaviours (Wilson et al., 2017), cultural venue and event attendance (Trinh & Lam, 2016), and industrial purchasing (McCabe & Stern, 2009;Uncles & Ehrenberg, 1990). ...
... An important feature of the model is that once fitted, under stable conditions it can be extended to describe the expected distribution of brand purchases in multiples of the original time period (Goodhardt & Ehrenberg, 1967), for example, to fit it for one quarter and extrapolate out to two quarters. Tests of NBD buying theory have often extended the model to novel contexts (Lam & Mizerski, 2009;Uncles & Ehrenberg, 1990) or decomposed buyer flows between two equal-length time periods (Wilkinson et al., 2016), but an obvious and important extension of repeat buying theory is to assess how closely the NBD estimates cumulative penetration, and the increase in light buying in the long-run. If successful, NBD theory provides benchmarks that link short term, annual, marketing objectives with strategic outcomes. ...
Although marketers are increasingly asked to manage brands for the long term, it is difficult to do so when no clear picture exists of long-term brand buying. This study reports cumulative behavioural loyalty outcomes for 200 UK consumer-goods brands when observed in a five-year household panel of continuous reporters. We examine these brands in intervals from one to five years against NBD (Negative Binomial Distribution) model projections. Stationary brands attract over twice as many buyers in five years as they do in one. Of these buyers, 80% purchase the brand at a rate of once a year or less, yet contribute 40% to total sales, a Pareto ratio of just 60:20. For managers, this light buying is broadly predictable from NBD fittings to annual data, and implies a renewed emphasis on nudging the brand buying propensities of the whole market.
... The Dirichlet model has been shown to accurately model a wide range of categories in differing times, countries, and conditions. It has been used to model the aggregate consumption patterns in categories as diverse as packaged goods (Goodhardt, Ehrenberg et al., 1984), industrial buying (Uncles & Ehrenberg, 1990;Pickford & Goodhardt, 2000), prescription of drugs (Stern & Hammond, 1997), credit card usage (Sharp, Wright, & Goodhardt, 2002), and store choice (Keng, Uncles, Ehrenberg, & Barnard, 1998). The following table adapted and updated from Ehrenberg, Uncles and Goodhardt (2004), neatly illustrates the variation in circumstances in which the Dirichlet model has been applied. ...
We present a review of Gerald Goodhardt's most famous contribution to marketing science—the NBD‐Dirichlet model. This provides a powerful illustration of the complex pathway and useful associated discoveries that over 25 years lead to the specification and application of a key marketing model. We identify the process that started with the negative binomial distribution (NBD) applied to purchase incidence, examined alternatives such as the logarithmic series distribution (LSD) and the beta binomial distribution (BBD), and along the way developed conditional trend analysis (CTA). We then explore the development of brand choice beginning with duplication of purchase as a method for understanding the underlying patterns, before moving into various approaches to modelling choice including a multivariate NBD, and eventually a multivariate BBD—the Dirichlet multinomial distribution (DMD). We discuss key events in modelling consumer behaviour and outline the model's implications for how marketers should think about consumers, or more specifically the Dirichlet consumer. Finally, we provide a survey of the model's applications uncovering a rich recent history and bright future for Goodhardt's legacy.
... Proposed segmentation variables are purchase responsibilities (Thomas, 1989), purchasing process and firm characteristics (Segal, 1989), customers' actual purchasing behavior (Dowling, Lilien, & Soni, 1994), and purchasing patterns of sourcing strategy (Frear, Alguire, & Metcalf, 1995). Other researchers consider buying behavior to determine price sensitivity (Ferrell et al., 1989) and to describe purchase frequency and brand choice (Uncles & Ehrenberg, 1990). Moreover, File and Prince (1996) consider the psychographic segmentation of family-owned firms. ...
Segmenting industrial markets is a key challenge for the marketing field. More than 30 years of research has not produced comprehensive guidelines for developing robust B2B market segments; only a few studies have empirically tested the impact of segmentation and the literature today appears to be more fragmented than earlier. The present study integrates prior endeavors via a systematic literature review, scrutinizing 88 papers in detail. It develops a three-layer framework comprised of: (1) conceptualization of B2B market segmentation, (2) segmentation as a process, and (3) context. The authors use the framework to evaluate scholarly efforts during the 1986-2019 period and propose a broader view on segmentation as a continuous process. Marketers can benefit from the study by adopting four activities for segmenting markets: (1) pre-segmentation, (2) segmen-tation, (3) implementation, and (4) evaluation. Finally, the authors identify several gaps and offer a rigorous, practice-oriented research agenda, providing direction for academicians.
... Plane purchases, aviation fuel contract purchases (Uncles and Ehrenberg, 1990) Doctors drug prescribing (Stern and Wright, 2015) Luxury purchases (Romaniuk and Sharp, 2016a) Highly fragmented markets like wine and media (Donthu, 1994; 2017) Subscription purchasing (Lee et al., 2011;Sharp et al., 2002) Tourism (Dawes et al., 2009) Sport (Baker et al., 2016) Charity/donation giving (Faulkner et al., 2016) Social media posts (Rogers et al., 2017) Social marketing, health and physical activity (Gruneklee et al., 2016) Attendance at sporting, arts and cultural events (Hand and Dall'Olmo Riley, 2016;Trinh and Lam, 2016) Gambling services (Lam and Mizerski, 2009) Tobacco (Dawes, 2012a) Polical polls (Kooyman and Wright, 2017) Broad range of countries including emerging markets (e.g. across Asia, Africa, South America) (Bennett and Graham, 2010;Uncles et al., 2012) Table 3 Areas being advanced by EG researchers. ...
At the end of the last century, documented the emergence of a school of marketing enquiry labelled as the Empirical Generalisationists. With this special edition on Empirically-Based Marketing Knowledge, we take the opportunity to update that original article, giving an overview on the health of the Empirical Generalisations research tradition. We put forward a call to action for more researchers to take up the challenge to develop scientific laws in marketing, and promote a culture of evidence-based theory and managerial decision making.
... Marketers know something about human behaviour, at least in the context of competitive consumers (and some B2B) markets (Keng, Uncles, Ehrenberg and Barnard 1998;Sharp, Wright and Goodhardt 2002;Uncles and Ehrenberg 1990). Buying behaviour in these markets can be characterized as choosing from a (limited) repertoire of a larger set of essentially similar options in an apparently random manner with relatively fixed propensities (at least in the short to medium term; Goodhardt, Ehrenberg, Chatfield 1984). ...
The Dirichlet model is an empirical generalization describing and predicting repeated choice amongst a set of competitive alternatives. With the advent of big data, there are many new potential applications for this model. Its developers emphasized one goodness-of-fit statistic, and subsequent researchers have used this along with others. There is, however, no consensus in the literature regarding which measures to use or, more importantly, benchmarks. This paper proposes a suite of six goodness-of-fit statistics developed from the literature to assess the fit of the model and develops two new measures that account for category specific factors enabling the development of benchmarks. It also provides appropriate benchmarks for all statistics derived from 54 FMCG categories in the UK.
... Other associated patterns have been found in consumer behaviour (Ehrenberg, 1988), transforming practice and increasing the credibility of the marketing function (Kennedy and McColl, 2012). Differentiated replications show law-like patterns exist in a wide range of markets and conditions (Ehrenberg, Uncles and Goodhardt, 2004), including aviation fuel contracts (Uncles and Ehrenberg, 1990) and gambling behaviour (Lam and Mizerski, 2009). ...
While there is no shortage of worthy recipients for prosocial behaviour, there is a constant battle to attract and keep donors. This research examines both money and blood donor behaviour for two key groups, new donors, (to grow the donor base), and frequent donors (to secure current support streams). We draw on over 1.2 million records from a U.S. health related charity for a three-year timeframe; and records of all Australian blood donors (1.1 million) for a five-year timeframe. We show the law-like patterns that underpin brand growth in other markets also apply in the non-profit sector. The vast majority of new donors give just once or twice a year with few giving at higher frequency levels. The stability of donation churn across blood and money suggests a structural norm in behaviour over time rather than an outcome of marketing activity. We discuss implications for resource allocation and marketing strategies.
... Moreover, several studies have reported unusually high repeat-purchase loyalty for PLs (e.g. Bound and Ehrenberg, 1997, Uncles, 2011) and future work, as outlined above, could examine the potential link between this high loyalty and high rates of PL sub-brand purchase duplication. ...
Purchase duplication analysis examines the extent to which buyers of any brand A also buy other brands B, C, D and so on. A generalised finding from its use is that brands share their buyers with other brands approximately in-line with the size of those other brands. The approach is widely used by analysts and managers. One important use of the method is to identify partitions – brands that share buyers at a higher than expected rate. Partitions may form among competitor brands, but also among ‘same name’ or sub-brands that share a parent name (e.g. Coke, Diet Coke). A partition among same-name brands means they are cannibalising each other. Whether one’s focus is on cannibalisation within a portfolio, identifying close competitors, or to generally understand market structure, duplication analysis can provide insights. However, there are two potential confounds to its use: family buying and buying multiple brands on the same occasion. This study tests if these two factors confound the use of purchase duplications, using data from 12 grocery categories. The principal finding is that the identification of partitions is robust to these confounds. The study finds partitions among same-name brands are common and are also not due to these confounds.
... Following on from the knowledge that consumers buy from a small repertoire 130 of brands, loyalty to these brands has been predicted accurately using empirical generalizations in various markets (e.g., Chatfield et al., 1966;Goodhardt & Ehrenberg, 1967;Keng et al., 1998;Uncles et al., 1995;Uncles & Ehrenberg, 1990). The availability and salience of larger brands leads to very predictable aggregate consumer purchase patterns. ...
This study aims to understand the consistency between attitudes toward ethical brands and consistency with the respondents' recent purchase behavior. A study of 202 respondents was carried out in order to observe consistency between claimed ethical attitudes and 15 self-reported purchase behavior across three product categories. Panel data (n = 8000) was utilized to provide a large sample on which a duplication of purchase analysis could be conducted. Results suggest many consumers claim to have ethical attitudes, but their reported purchases suggest their behavior is not consistent. 20 Consumers who purchase fair trade brands are just as likely to purchase other, non–fair trade brands.
... The overall results are consistent with, and extend, past research. Research into packaged goods (Ehrenberg et al., 2004) durables (Colombo et al., 2000) and in a B2B application (Ehrenberg, 1975, Uncles andEhrenberg, 1990b) and banks (Wright and Riebe, 2010) has identified the strong effect of size on brand switching. One previous study found an absence of perceptionsbased brand partitions (Sharp and Sharp, 1997), but had not examined the role of context in influencing market structure. ...
Purpose
– The purpose of this paper is to determine if services brands such as banks share their customers with competing brands in line with the market share of those competitors, and whether services brands with similar images form market partitions with heightened competitive intensity.
Design/methodology/approach
– The study uses brand usage, forced-choice and brand perceptions data obtained from a survey of consumers. The study uses a log-linear modelling framework to identify market structure and to test if partitions correspond to similarities in brand image.
Findings
– Analysis of in-market data shows customers share their requirements between competing brands in line with market share, and that brands with similar images do not form partitions. However, when consumers are asked to choose brands for a specific product, there is some tentative evidence of brand partitions among brands with similar brand image.
Practical implications
– The results here can help managers in service markets such as banking and insurance understand market structure. As a result, they can better plan customer acquisition and retention strategies.
Originality/value
– The study addresses a lack of research into customer sharing and switching in services markets. No previous study has successfully employed brand-sharing, forced-choice and brand image data to identify market structure in a services context.
... There is some evidence to suggest that at least some non-packaged-goods markets can be thought of in this way; for example, empirical studies of industrial contracts and motor car buying (Ehrenberg and Pouilleau 1992;Uncles and Ehrenberg 1990) and speculation about airline markets (Dowling and Uncles 1997). But, as yet, the evidence is limited. ...
Patterns of behaviour among executive airline travellers are described. Evidence shows that: (a) airlines are chosen habitually by executive travellers from among small individual split-loyalty repertoires; (b) competitive brands are seen as closely substitutable; and (c) route/schedule convenience emerges as the crucial driver of choice. In certain respects these patterns of behaviour mirror those found in "Dirichlet-type markets" and the implications of this are discussed briefly.
... It has also been used in markets with less frequent purchase patterns, such as electrical goods (Bennett, 2004) and motor vehicles (Colombo et al., 2000). Service contexts have also been examined: quick service restaurants (Bennett and Ehrenberg, 2002) retail store choice by consumers (Uncles and Ehrenberg, 1990a) and mixed service/goods provision in a B-to-B setting (Ehrenberg, 1975b;Uncles and Ehrenberg, 1990b). The basic premise of the duplication of purchase law also appears in the literature under other names. ...
Purpose
The purpose of this paper is to examine competition between tourism destination brands in terms of how they share travelers with each other.
Design/methodology/approach
The study analyzes survey data from four international markets (USA, UK, Japan and Singapore). The study examines the cross‐purchasing of travel destinations. It applies an established empirical generalization, the duplication of purchase law (DPL) to frame hypotheses and contextualize results.
Findings
The overall results are consistent with the DPL. Destination brands share tourists with other destinations generally in‐line with the popularity of the competing destination. However, there are very noticeable market partitions, most of which take two forms: destinations that are either geographically close to each other, or close to the point of origin. Destination brands in these partitions share travelers far more than they would be expected to, given their respective size.
Practical implications
Tourism marketers need to appreciate the broad nature of competition. A specific destination brand competes with many other travel destinations, sharing customers more with other broadly popular destinations and less with less popular destinations.
Originality/value
The analytical approach presented in this study provides a straightforward benchmark for assessing the expected level of competition between particular tourist destinations, given their respective overall popularity.
... Industrial purchasing and procurement-isolated cases so far, such as chemical additives, paper and packaging (Easton, 1980), aviation fuel contracts (Uncles and Ehrenberg, 1990b), and ready mix concrete (Pickford and Goodhardt, 2000). Store choice-repeat visits and switching between grocery outlets (Kau and Ehrenberg, 1984;Kau et al., 1998;Uncles and Ehrenberg, 1990a;Dunn, 1984, 1985), womenswear retailing (Brewis-Levie and Harris, 1999), and recently on-line electronic shopping (Danaher et al., in press;Moe and Fader, 2001). SKUs-customer retention and switching between stockkeeping units, such as specific combinations of pack sizes, flavors, and model specification (as for cars or PCs). ...
Sales of a brand are determined by measures such as how many customers buy the brand, how often, and how much they also buy other brands. Scanner panel operators routinely report these “brand performance measures” (BPMs) to their clients. In this position paper, we consider how to understand, interpret, and use these measures. The measures are shown to follow well-established patterns. One is that big and small brands differ greatly in how many buyers they have, but usually far less in how loyal these buyers are. The Dirichlet model predicts these patterns. It also provides a broader framework for thinking about all competitive repeat-purchase markets—from soup to gasoline, prescription drugs to aviation fuel, where there are large and small brands, and light and heavy buyers, in contexts as diverse as the United States, United Kingdom, Japan, Germany, and Australasia.Numerous practical uses of the framework are illustrated: auditing the performance of established brands, predicting and evaluating the performance of new brands, checking the nature of unfamiliar markets, of partitioned markets, and of dynamic market situations more generally (where the Dirichlet provides theoretical benchmarks for price promotions, advertising, etc.). In addition, many implications for our understanding of consumers, brands, and the marketing mix logically follow from the Dirichlet framework. In repeat-purchase markets, there is often a lack of segmentation between brands and the typical consumer exhibits polygamous buying behavior (though there might be strong segmentation at the category level). An understanding of these applications and implications leads to consumer insights, imposes constraints on marketing action, and provides norms for evaluating brands and for assessing marketing initiatives.
The advice to musicians and marketers is to focus on what they love: a truism for practitioners is to find 1000 ‘true fans’ and make $100 from each of them (Kelly, 2008. 1000 True fans. The Technium). If this advice is correct, we should see musicians with loyal user bases engaging more with their favourite artists and less with other music, suggesting a narrow targeting strategy would suffice. On the other hand, the established marketing laws indicate that the listeners of very different genres should overlap more than conventional wisdom would suggest, supporting the need for a much broader approach to targeting potential audiences. Given these conflicting views, musicians need to know if they should market to their existing listeners, the listeners of music similar to theirs (i.e., the same genre), or if they should try to reach a much wider audience. We turn to established choice patterns from the marketing literature to address these questions in the music context. This study examines 84,000,000 observations of music listening from 27,000 unique global users between 2013 and 2014 and survey data from 2019 containing music listening from over 1000 representative respondents in the United States. The results show that listening follows the Duplication of Purchase law for genres, artists, albums, and songs, at an annual, 6‐months, 3‐months, 1‐month, and 1‐week period, with no indication of partitioned music listening. The implication is that musicians should try to reach all potential listeners, regardless of what they already listen to. These findings contribute to the theoretical knowledge about duplication analyses of various durations, extend the contexts of choice behaviour that exhibit this pattern, and managerially, to knowledge about the extent of potential audiences and ‘share of ear’ competition.
Based on the analysis of two sets of data (a cross-sectional online survey of five product categories with an average sample size of 525 and a longitudinal telecommunications panel of more than two million respondents), this study detects a positive relationship between the market size (purchase penetration) of Iranian e-brands (or websites) and the percentage of customers shared with other e-brands. This finding is consistent with the well-established Duplication of Purchase Law; it also holds over time and across different markets (e.g., repertoire vs. subscription). Hence, this study makes a twofold contribution to marketing knowledge. First, it expands the collection of empirical evidence concerning the Duplication of Purchase, which thus far is primarily within offline contexts and Western countries. Second, it addresses issues inherent to research on e-loyalty, such as the over emphasis on evaluating loyalty for one e-brand at a time via complex attitudinal measures. Accordingly, this study advances consumer buying behaviour research by clarifying that, similar to offline domains and other geographical areas, e-loyalty in this buoyant Middle Eastern market divides across a small number of e-brands. It is also best appraised through behavioural loyalty and by comparing multiple e-brands competing within the same market. These outcomes translate into a series of practical guidelines for the strategic management of e-brands, improving the practical understanding how e-brands compete and grow.
Die Frage, wie sich das Loyalitätsverhalten von Firmenkunden im Corporate Banking im Kontext der Beziehungsdyade zu Bank und Kundenberater entwickelt, steht im Mittelpunkt der Arbeit. Auch die entsprechenden Größenunterschiede der Firmenkunden werden betrachtet. Zur Beantwortung der Forschungsfragen wird ein Loyalitätsmodell entwickelt und mittels der Service Dominant Logic über die Ebenen Bank und Kundenberater projeziert. Die empirische Untersuchung wird mittels Strukturgleichungsmodell durchgeführt. Es zeigt sich, dass die Entwicklung der Loyalität zum Kundenberater keine Durchgängigkeit bis hin zur Verhaltensloyalität aufzeigt. Dies ist bei der Loyalität zur Bank hingegen der Fall, jedoch nur für kleinere Firmenkunden. Die Unternehmensgröße zeigt generell einen starken negativen Einfluss auf die Verhaltensloyalität.
This paper explores buying behaviour for an infrequently purchased capital equipment product. The extent to which the observed data fits a Negative Binomial Distribution of purchase incidence is assessed. The analysis shows that repeat buyers account for a relatively small proportion of purchases.
Purpose
This paper aims to extend the known boundary conditions of the negative binomial distribution (NBD) model, and to test the applicability of conditional trend analysis (CTA) – a key method to identify whether changes in overall sales are accounted for by previous non-buyers, light buyers or heavy buyers – in industrial purchasing situations.
Design/methodology/approach
The study tested the NBD model and CTA in an industrial marketing context using a 12-month data set of purchases from an Australian supplier of a range of industrial plastic resins.
Findings
The purchase data displayed a good NBD fit; the study therefore extends the known boundary conditions of the model. The application of CTA provided second-period purchasing frequency estimates showing no significant difference from actual data, indicating the applicability of this method to industrial purchasing.
Research limitations/implications
Data relate to just one supplier. Further research across several industries is required to confirm the generalizability and robustness of NBD and CTA to industrial markets.
Practical implications
Marketing decisions can be improved through appropriate analysis of customer purchasing data. However, without access to equivalent competitor data, industrial marketers are constrained in benchmarking the purchasing patterns of their own customers. The results indicate that use of the NBD model enables valid benchmarking for industrial products, while CTA would enable appropriate analysis of purchases by different classes of customer.
Originality/value
This paper extends the known boundary conditions of the NBD model and provides the first published results, indicating the appropriateness of CTA to predict purchasing frequencies of different industrial customer classes.
We show that commercial aircraft customers buy aircraft brands probabilistically and that their aggregate buying patterns conform to the well-known double jeopardy and duplication of purchase laws. This is a major conceptual contribution to the analysis of industrial buyer behavior with important implications for industrial marketing management. Analysis using stochastic models of brand choice with consumer panel data is the norm in fmcg categories, but the lack of such data in industrial markets should not be seen as insuperable; a variety of data gathering techniques make it possible to assemble sufficient data even in markets where purchases are spread out over many years. Thus our second contribution is to show that competitive market structure can be revealed by data readily available to marketing managers that can be analyzed simply, with basic analysis tool, but with profound managerial implications.
Two key law-like patterns – the double jeopardy and duplication of purchase laws – have consistently been found to explain and predict consumer behavior across a wide range of industries. There has been speculation that these empirical generalisations may not hold in the case of professional team sport brands. The reasons given include the passionate loyalty of sport fans, the fact that two sport teams must be consumed at once in any contest, and the strong geographic dominance of sport brands. In this study, we examine the applicability of these two law-like generalisations to professional team sport. With a few caveats, these law-like patterns hold, suggesting that sport team brands operate in line with what is known about other consumer markets. Results suggest the unique aspects of the sport market do not meaningfully impact consumer behavior and therefore sport brands should be managed in fundamentally the same way as most consumer markets.
I have been asked by the editors to contrast two current research traditions in marketing, what I call the theoretical-in-isolation or TiI and the empirical-then-theoretical or EtT approaches. First I will define the two approaches, give examples especially of the less well-documented EtT, describe a more advanced research tradition (ETET...), and comment on my rather black-and-white evaluation of TiI (no good) and EtT (good). I will then set out the main characteristics of the two traditions as I see them, illustrate differences between TiI and EtT in terms of research into buying behavior, and note how EtT, unlike TiI, seems to have led to routinely predictable results, to grounded theory, and to a range of practical applications.
Purpose
– The purpose of this research is to analyze brand competition in China using the Duplication of Purchase (DoP) law, with important implications for understanding Chinese buyer behavior in comparison with Western buyers. Discovered in the Western markets, the DoP law holds across a variety of product categories.
Design/methodology/approach
– Multiple sets of new data are examined to extend past research in the application of the DoP law in Chinese buying behavior. This study draws on panel data and self-reported data, utilizing bootstrapping to identify partitions where excess sharing occurs.
Findings
– This paper finds the DoP law holds across six categories (two personal care, two impulse categories and two durables), as well as over multiple years. Brands in China share customers with other brands in line with the market share of the competitor brand. There were few partitions where brands shared significantly more customers than expected. Partitions occur due to the same umbrella brand or ownership, and geographic location.
Research limitations/implications
– Areas for further research include extended replication in other categories, investigating partitions and whether a different consumer path to purchase occurs in China.
Practical implications
– DoP can be applied across a wide range of categories in China to understand market structure. New entrants to China can use this approach to understand a category from a consumer behavior perceptive. DoP provides guidelines for marketers to identify competition and allocate resources appropriately.
Originality/value
– This research provides a comprehensive, unparalleled examination across six very different categories of brand competition in China. This gives confidence in the robustness and generalizability of the results.
The phenomenon of double jeopardy is commonly manifested in the structure of competitive markets where items differ in their popularity. It is defined as a phenomenon in which more-popular brands not only enjoy more buyers, but also have buyers who are more loyal. Conversely, less-popular brands are chosen by a smaller number of buyers. The jeopardy is doubled because the smaller, less-popular brands are purchased less often and in smaller quantities by their fewer buyers. This paper provides results from a study that tested for attitudinal and behavioral patterns of double jeopardy for furniture-related trade shows. Data indicate that smaller, less-popular trade shows suffer from regular patterns of double jeopardy much the same as those encountered in consumer goods. Managers in any forest-based industry can use this information to recognize the existence of double jeopardy patterns and to understand ramifications for their position within a given market.
Because exhibition organizers face a stochastic environment, they find it difficult to predict exhibitors' future purchases of exhibition booths. With competition increasingly cutthroat and customer churn problems on the rise, many exhibition organizers now recognize the importance of customer relationship management and regard the efficacy of transaction forecasting as the basis for such management. This article examines the beta-geometric/negative binomial distribution (BG/NBD) model, which is a transaction forecasting model, and specifically discusses its empirical validation and applicability for predicting exhibitors' repeat purchases in the exhibition industry.
L'étude et la modélisation du comportement d'achat du client industriel constituent le fondement majeur sur lequel a pu se développer la théorie en marketing industriel à partir de la fin des années soixante.
Les années quatre-vingt ont vu l'émergence et le développement de deux nouveaux courants de recherche sur le sujet : le courant inductif et le courant interactif. Méthode d'investigation différente pour l'un, objet d'investigation délimité différemment pour l'autre, les apports de ces deux courants, présentés ici, participent ainsi d'une vision pluraliste nécessaire à l'étude du phénomène complexe qu'est le comportement d'achat industriel.
The Dirichlet is a well-established theoretical model that describes and predicts patterns of purchasing behavior in stationary markets. This paper uses data from a highly nonstationary market to demonstrate that the Dirichlet norms also provide a baseline to interpret change in purchasing behavior in particular, change wrought by sustained promotional activity. The empirical analysis of industrial purchasing data describes how one supplier more than doubled its share of the market. This share increase was achieved by, first, securing a higher share of the category purchases made by heavy buyers (increasing purchase frequency) before adopting a more typical growth strategy of attracting more buyers (increasing penetration).
Researchers have spent almost 50 years developing, refining and applying the NBD-Dirichlet in repeat purchase markets, in particular with extensive replication of the Goodhardt, Ehrenberg, and Chatfield (1984) model. Recent research that employs a double jeopardy (DJ) line appears to have progressed with little regard for this body of theory. This paper reviews the varied applications of the NBD-Dirichlet and extends the theory to the portrayal of a double jeopardy line. This DJ line, an x–y plot of brands' penetration versus purchase frequency in a category, is tested against three alternative ways of drawing the line. A linear model for double jeopardy is adequate when used under limited conditions yet the model breaks down with a broad scope of analysis. This meta-analysis of 37 cross-sectional product categories and a 40-period (quarters) longitudinal dataset evaluates the best approximation of the DJ line to empirical data.Double Jeopardy then appears as an upward sloping curve, rather than a DJ line. The NBD-Dirichlet provides for a theoretically sound, versatile method whose parameters have intuitive meanings regarding seasonality, category acceptance and category loyalty.
SMC models are a group of models to forecast customer's buying behaviors provided in 1987. If SMC models are proved to be true, they are very valuable to design analytical CRM (customer relationship management) systems. Choosing IT distribution market industry as background, an empirical research is done in this paper. We selected 331 customers to test SMC models. The conclusion is that SMC models do work in IT distribution market industry. They have a relative high prediction precision. The application of SMC models in CRM and the revising advice for SMC is also put forward
This study investigates brand loyalty and other brand performance metrics in the UK sportswear market. It utilizes consumer purchase data kindly provided by Taylor Nelson Sofres. The study finds that empirical regularities discovered by Andrew Ehrenberg and colleagues apply to sportswear brands - including iconic brands such as Nike and Adidas. The main findings are that (1) sportswear brands enjoy polygamous loyalty from their buyers; (2) the market exhibits the classic double jeopardy pattern whereby smaller brands have slightly lower loyalty; (3) consumers switch between sports brands approximately in-line with their market share; and (4) a brand’s performance with respect to any demographic-based consumer sub-group is approximately the same as it is in the population generally. That is, sportswear brands tend not to have markedly different appeal to particular demographic segments. Therefore, even iconic brands and self-expressive, emblematic product categories show predictable patterns in brand performance. These well-documented empirical patterns should be used by research providers and brand managers to contextualize brand performance.
In recent years, there have been calls for more emphasis on empirical generalisations in marketing. An empirical generalisation is a ‘pattern or regularity that repeats over different circumstances’.1 Empirical generalisations are important for marketers. They provide a fact base from which to work, and are distinguished from mere opinions—even very learned or considered opinions. Three empirical generalisations to be discussed in this paper originated from the work of Ehrenberg and his colleagues. They are (1) repertoire buying, (2) the ‘double jeopardy’ phenomenon and (3) the duplication of purchase law. While many studies have demonstrated these generalisations, more evidence from other markets and conditions would be useful. Indeed, marketing textbooks typically do not discuss these findings, which limits the chance that practitioners become aware of them. This study examines whether these three established generalisations hold in quite a different market to those considered previously—the market for beer in Australia. Local market wisdom and other published research casts doubt over their applicability to this market. Therefore this study can either identify an exception to these generalisations, or find that they do apply where arguably they would not be expected to apply. The study finds that Australian beer drinkers do buy from repertoires of brands, that the brands do exhibit the classic double jeopardy pattern in loyalty, and that the duplication of purchase law also holds in this market. Therefore Ehrenberg's findings hold in another new context, one in which they were not necessarily expected to. The implications from these findings are that marketers should not expect many of their buyers to be very loyal, rather they should view them as people who occasionally buy their brand among a portfolio of other competing brands. Secondly, marketers should recognise that brand loyalty metrics are largely dictated by market share levels, and that somewhat lower levels of loyalty to smaller brands are to be expected. Thirdly, marketers should view their competition more widely and not focus too much on any one specific competitor brand. Rather, brands usually compete with all other brands in the market approximately in-line with the size of those other brands. This is to be expected unless there are marked functional differences between the competing brands.Journal of Brand Management (2008) 15, 198–208. doi:10.1057/palgrave.bm.2550099; published online 22 June 2007
Yes, this article is ambitious in covering fifty years of OBB theory and research before and after 2006. "Fools rush in where angels fear to tread" comes readily-to-mind. Still, explicitly identifying and reflecting on landmark contributions in the literature likely helps to increase the quality of sensemaking as to where OBB theory and research is heading in the decades ahead. 1956 is an important OBB milestone because it included the publication of Cyert, Simon, and Trow's "observation of a business decision" - a call for a descriptive theory of "how real human beings go about making choices in the real world." CST (1956) illustrate propositions in their rudimentary descriptive theory via a thick description of one organisation's real-life process in deciding on (not) buying a mainframe computer. CST's landmark contribution follows a comparative method case-based logic of examining the fit between the rational-choice process theories with real-life process data. The OBB literature since 1956 includes deepening and extending of core propositions in CST's early descriptive theory building. These advances include Mintzberg, Raisinghani, and Theoret's (1976) mapping the "structure of unstructured decision-making," von Hippel's (1986) lead-user's drive innovation proposal, Biemans (1991) identifying third-party influences in buying new technologies, Langley, Mintzberg, Pitcher, Posada, and Saint-Macary, (1995) "opening-up decision making theory to include seemingly random context influences, and other important milestones." The present article's sensemaking of the 1956-2006 literature informs the building of case-based reasoning models that goes beyond the arguing among empirical positivists versus existential phenomenologists to a bright future that includes system dynamics and mixed methods research strategies.
In this study we compare consumer brand loyalty in online and traditional shopping environments for over 100 brands in 19 grocery product categories. The online purchase data come from a large traditional grocery retailer that also operates an online store for its products. The offline data corresponds to the exact same brands and categories bought in traditional stores by a panel of homes operated by ACNielsen for purchases made in the same city and over the same time period. We compare the observed loyalty with a baseline model, a new segmented Dirichlet model, which has latent classes for brand choice and provides a very accurate model for purchase behavior. The results show that observed brand loyalty for high market share brands bought online is significantly greater than expected, with the reverse result for small share brands. In contrast, in the traditional shopping environment, the difference between observed and predicted brand loyalty is not related to brand share.
Customer base analysis is concerned with using the observed past purchase behavior of customers to understand their current and likely future purchase patterns. More specifically, as developed in Schmittlein et al. (1987), customer base analysis uses data on the frequency, timing, and dollar value of each customer's past purchases to infer
• the number of customers currently active,
• how that number has changed over time,
• which individual customers are most likely still active,
• how much longer each is likely to remain an active customer, and
• how many purchases can be expected from each during any future time period of interest.
In this paper we empirically validate the model proposed by Schmittlein et al. In doing so, we provide one of the few applications of stochastic models to industrial purchase processes and industrial marketing decisions. Besides showing that the model does capture key aspects of the purchase process, we also present a more effective parameter estimation method and some results regarding sampling properties of the parameter estimates. Finally, we extend the model to explicitly incorporate dollar volume of past purchases.
Our results indicate that this kind of customer base analysis can be both effective in predicting purchase patterns and in generating insights into how key customer groups differ. The link of both these benefits to industrial marketing decision making is also discussed.
This paper investigates the common ground between two apparently contrasting approaches to the understanding of organizational
purchasing behavior; stochastic modelling and the IMP (or “markets as networks”) approach. These two schools of inquiry have
travelled along parallel tracks for many years but there has never been a systematic attempt to analyse the ontological, epistemological
and methodological similarities between them. We present a coherent theoretical framework to investigate the common ground
between stochastic modelling and IMP and demonstrate that the two approaches offer complementary insights that can and should
be exploited in the context of research into organizational purchasing behavior.
Empirical regularities in buying behavior observed in mostly consumer markets have been linked into a comprehensive model, the Dirichlet. No attempt has yet been made to see if this model applies to services in general or to business-to-business services in particular. In this paper, we examine the purchasing behavior of large multinational corporations from four countries who purchase foreign exchange contracts from the major banks. We highlight similarities to the patterns of buying behavior observed in consumer markets. Implications for the management of business-to-business services firms are discussed.
The numbers buying, the brand penetrations, go down by a factor of 10. The average number of times each brand is bought also goes down (with some small wobbles, e.g. Bounce), though much less so − by a factor of less than 2. This pattern is ubiquitous and has long been called Double Jeopardy (DJ). The small brand is "punished twice" for being small: it has fewer buyers, and its fewer buyers also buy the brand some-what less loyally. The wide occurrence of DJ has never been queried. One reason is that DJ can easily be seen in one's own data. In many markets even the big-gest brand has a fairly low penetration (say 20% per year, instead of 48% for Downy). In such cases, the DJ variation in the buying rates is generally very small (e.g. from 2.8 down to 2.3). This is often condensed into: Large and small brands differ greatly in how many people buy them, but not in how loyal they are.
The Dirichlet is a stochastic model of purchase incidence and brand choice which parsimoniously integrates a wide range of already well-established empirical regularities.
Consumers show low store loyalty and little or no segmentation between different chains or store groups when buying a grocery product in the United Kingdom. Store penetration, repeat buying of the product at the same store group, and multistore buying all follow the same theoretical patterns as have been established previously for brands. Store choice is like brand choice. Loyalty to a specific brand within a particular chain is also low. Over time, people spread their purchases of the product extensively to other brands and other chains directly in line with market shares.
A review of what the author calls "significant progress" toward sophisticated models and measurement techniques in this field.
This paper presents one of the first attempts to develop stochastic models of industrial buying behaviour. The Beta-binomial model, used to model consumer purchase incidence, also works well for industrial consumers. Purchase size is shown to be lognormally distributed suggesting that something like a log random walk process may be operating. However it proved impossible to combine these two stochastic models analytically and a less rich model, the Markov reservoir, was shown to fit the data providing useful insights into the dynamics of industrial markets as well as suggesting areas for further research.
A model for marketing and pricing under competitive bidding
- Simmonds
Patterns of store-choice: New evidence from the USA
- Uncles
Patterns of buying. Unpublished Ph.D. Thesis
- G Easton
Easton, G., 1975. Patterns of buying. Unpublished Ph.D. Thesis, London Business School, Regent's Park, London NW1
4SA, U.K.
Essays on understanding buyer behavior
- G A S C J Ehrenberg
- Goodhardt
Ehrenberg. A.S.C. and G.J. Goodhardt, 1977. Essays on understanding buyer behavior. J. Walter Thompson/the Market
Research Corporation of America.
A comparison of brand loyalty and store loyalty. Working Papers
- T J Lamb
- G J Goodhardt
Lamb, T.J. and G.J. Goodhardt, 1988. A comparison of brand
loyalty and store loyalty. Working Papers, City University
Business School, London, EC2Y 8HB, U.K.
A model for marketing and pricing under competitive bidding
- P J Robinson
- C W Faris
- Y Wind
Robinson, P.J., C.W. Faris and Y. Wind, 1967. Industrial
buying and creative marketing. Boston, MA: Allyn &
Bacon.
Simmonds,
.S., 1965. A model for marketing and pricing
under competitive bidding. In: New directions in marketing. Chicago: American Marketing Association.