Cluster Analysis in Marketing Research: Review and Suggestions for Application

Punj, Girish; Stewart, David W.

doi:10.2307/3151680

Cited by 1,313 publications

(350 citation statements)

References 70 publications

Supporting

Mentioning

330

Contrasting

Unclassified

Order By: Relevance

“…Examination of the dendrograms, agglomeration plots, and changes in agglomeration coefficients for the complete-linkage, average linkage, and Ward's method algorithms supported a five-cluster solution. Upon comparison of hierarchical algorithm results, the Ward's method best fit the data, which is consistent with scholars' preference for the Ward's method [9,36]. Average values of the 14 standardized classification variables for each of these five solution groups were used as initial seeds for a nonhierarchical cluster analysis, the solution of which produced five groups with 45, 39, 16, 9, and 5 members, respectively.…”

Section: Taxonomic Analysissupporting

confidence: 58%

“…A two-stage approach used the results of the optimal hierarchical solution as initial cluster centroids for a nonhierarchical cluster analysis [35,36]. The final K-means cluster solution was tested for reliability through comparison of results across multiple cluster analyses, including solutions from the hierarchical algorithms and solutions using different approaches to address variable standardization and multicollinearity.…”

Section: Taxonomic Analysismentioning

confidence: 99%

See 1 more Smart Citation

Clustered and distinct: a taxonomy of local multihospital systems

Shay

Mick

2016

Health Care Manag Sci

View full text Add to dashboard Cite

Despite their prevalence and power in markets throughout the United States, local multihospital systems (LMSs) -also referred to as hospital-based "clusters" -remain an understudied organizational form, with studies instead primarily focusing either upon individual hospitals or viewing hospital systems collectively without distinguishing the local "sub-systems" that comprise larger regional or national hospital chains. To better understand these organizational forms, we develop a taxonomy specifically devote to LMSs, applying taxonomic analysis methods to a sample of LMSs in six U.S. states while accounting for LMSs' geographic arrangements and nonhospital-based service locations. Our analysis identifies five distinct LMS categories, with forms clearly distinguished according to their varying degrees of differentiation and integration. The study's results accentuate the importance of accounting for hospital systems' activities and arrangements in local markets -including their non-hospital-based sites -and highlight differences in systems' achievement of integration and coordination across services and locations, providing considerations in light of U.S. health system reform as well as international patterns of regional system formation.

show abstract

Section: Taxonomic Analysissupporting

confidence: 58%

Section: Taxonomic Analysismentioning

confidence: 99%

Clustered and distinct: a taxonomy of local multihospital systems

Shay

Mick

2016

Health Care Manag Sci

View full text Add to dashboard Cite

show abstract

“…Early applications of market segmentation through cluster analysis seemed to grow rapidly ahead of the empirical understanding of the technique and without a firm theoretical basis. Punj and Stewart (1983) provided clarification on this issue in an effort to alleviate the confusion by producing a series of guidelines on the appropriate application of cluster analysis. However, Dibb and Stern (1995) express persisting concerns related to the reliability of segmentation solutions based on cluster analysis, arguing that researchers need to ensure that their approach is based on theoretical principles to avoid spurious results.…”

Section: Overview Of Segmentation Approachmentioning

confidence: 99%

Consumer structure in the emerging market for electric vehicles: Identifying market segments using cluster analysis

Morton

Anable

Nelson

2016

International Journal of Sustainable Transportation

View full text Add to dashboard Cite

Article:Morton, C orcid.org/0000-0003-0984-9580, Anable, J orcid.org/0000-0002-4259-1641 and Nelson, J (2017) Consumer Structure in the Emerging Market for Electric Vehicles: Identifying market segments using cluster analysis. International Journal of Sustainable Transportation, 11 (6 ReuseUnless indicated otherwise, fulltext items are protected by copyright with all rights reserved. The copyright exception in section 29 of the Copyright, Designs and Patents Act 1988 allows the making of a single copy solely for the purpose of non-commercial research or private study within the limits of fair dealing. The publisher or other rights-holder may allow further reproduction and re-use of this version -refer to the White Rose Research Online record for this item. Where records identify the publisher as the copyright holder, users can verify any specific terms of use on the publisher's website. TakedownIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing eprints@whiterose.ac.uk including the URL of the record and the reason for the withdrawal request. 1 Consumer Structure in the Emerging ABSTRACTThis paper presents results from a segmentation analysis of the emerging market for Electric Vehicles (EVs). Data has been sourced through the application of a self-completion household questionnaire distributed over two cities in the United Kingdom (UK). A two stage cluster analysis methodology has been followed to identify market segments in a dataset of UK drivers. Five unique segments have been identified in the analysis and are characterised by their preferences for EVs, socio-economic characteristics, current car details, and socio-psychological profiles. These segments hold a range of different EV preference levels, from those who appear unwilling to adopt an EV to those which are clearly attracted to EVs. Moreover, the features of these segments tend to suggest that segments might be attracted to or repelled from EVs for different reasons. These results demonstrate that a significant degree of consumer stratification is present in the emerging market for EVs, with the possible implications being that policy interventions at the market, as opposed to segment, level may prove ineffective due to their inability to cater for the nuances of important segments.

show abstract

“…The kmeans algorithm is perhaps the most popular method for non-overlapping clustering (Wedel & Kamakura, 1998). When compared to other non-overlapping clustering methods, it appears to be more robust against outliers and is less afflicted by irrelevant variables or dimensions in the data (Punj & Stewart, 1983). It is also efficient in dealing with large data sets (Green, Carmone, & Kim, 1990).…”

Section: Introductionmentioning

confidence: 99%

An Extension of Multiple Correspondence Analysis for Identifying Heterogeneous Subgroups of Respondents

et al. 2006

View full text Add to dashboard Cite

An extension of multiple correspondence analysis is proposed that takes into account cluster-level heterogeneity in respondents' preferences/choices. The method involves combining multiple correspondence analysis and k-means in a unified framework. The former is used for uncovering a low-dimensional space of multivariate categorical variables while the latter is used for identifying relatively homogeneous clusters of respondents. The proposed method offers an integrated graphical display that provides information on cluster-based structures inherent in multivariate categorical data as well as the interdependencies among the data. An empirical application is presented which demonstrate the usefulness of the proposed method and how it compares to several extant approaches.

show abstract

Cluster Analysis in Marketing Research: Review and Suggestions for Application

Cited by 1,313 publications

References 70 publications

Clustered and distinct: a taxonomy of local multihospital systems

Clustered and distinct: a taxonomy of local multihospital systems

Consumer structure in the emerging market for electric vehicles: Identifying market segments using cluster analysis

An Extension of Multiple Correspondence Analysis for Identifying Heterogeneous Subgroups of Respondents

Contact Info

Product

Resources

About