Search results

1 – 10 of over 9000
Content available
Article
Publication date: 14 May 2020

Bambang Eka Cahyana, Umar Nimran, Hamidah Nayati Utami and Mohammad Iqbal

The purpose of this study is to apply hybrid cluster analysis in classifying PT Pelindo I customers based on the level of customer satisfaction with passenger services of…

Abstract

Purpose

The purpose of this study is to apply hybrid cluster analysis in classifying PT Pelindo I customers based on the level of customer satisfaction with passenger services of PT Pelindo I.

Design/methodology/approach

Hybrid cluster analysis is a combination of hierarchical and non-hierarchical cluster analysis. This hybrid cluster analysis appears to optimize the advantages of hierarchical and non-hierarchical methods simultaneously to obtain optimal grouping. Hybrid cluster analysis itself has high flexibility because it can combine all hierarchical and non-hierarchical methods without any limits in the order of analysis used.

Findings

The results showed that 72% of PT Pelindo I customers felt PT Pelindo I service was special, while the remaining 28% felt PT Pelindo I service was good.

Originality/value

In total, 117 customers of PT Pelindo I were involved in a study using the non-probability sampling method.

Details

Journal of Economics, Finance and Administrative Science, vol. 25 no. 50
Type: Research Article
ISSN: 2077-1886

Keywords

To view the access options for this content please click here
Article
Publication date: 1 July 1980

J.A. Saunders

Examines the processes of cluster analysis and describes them using an example of benefit segmentation, and also discusses other applications suggesting new directions of…

Abstract

Examines the processes of cluster analysis and describes them using an example of benefit segmentation, and also discusses other applications suggesting new directions of research in related fields. Bases an example study with 200 early respondents to a survey into sixth formers' choice of degree course, in which students were given 23 criteria which related to their course choice. Comparisons of likeness using Euclidean distance measures were employed. Uses also importance ratings given by three drivers to characteristics of new cars. Proposes that hierarchical clustering can be criticised when used to cluster data that is not naturally hierarchical, but other procedures have similar failings. Posits that clumping and optimisation in conjunction with hierarchical clustering offer the greater potential. Concludes that cluster analysis is a flexible tool, which provides a number of opportunities for marketing, and it is an appealing and simple idea ‐ but there are many technical questions that a researcher must ask before it is used.

Details

European Journal of Marketing, vol. 14 no. 7
Type: Research Article
ISSN: 0309-0566

Keywords

To view the access options for this content please click here
Article
Publication date: 3 October 2008

Grant Samkin and Annika Schneider

The purpose of this paper is to illustrate how qualitative data may be analysed using a method that can be considered as rigorous/scientific as any statistical analysis of…

Abstract

Purpose

The purpose of this paper is to illustrate how qualitative data may be analysed using a method that can be considered as rigorous/scientific as any statistical analysis of quantitative data.

Design/methodology/approach

An artificial neural network programme CATPAC II™ was used to evaluate selected portions of two accounting standards: the Financial Reporting Standards Board of New Zealand's standard on consolidation; and the equivalent standard developed by the International Accounting Standards Committee and revised by the International Accounting Standards Board.

Findings

The analysis of the concepts of control in the two standards identifies the differences that exist between the two standards. These differences are illuminated through the use of a hierarchical cluster analysis of 40 unique concepts in each of the two standards and 2D representation of the concepts. The extent of the differences in the concepts was established through a rotational analysis of the two datasets.

Research limitations/implications

This research is limited to the analysis of the concept of control and associated commentary paragraphs and supporting documents associated with two accounting standards. Different results may have been obtained had the whole standard been analysed.

Practical implications

Artificial neural network software can be used to support the intuitive textual understanding of the differences that exist in qualitative data. In this paper, the differences identified in the concepts of control may result in different interpretations being taken by the accounting standard users when determining what reporting entities to include in consolidated financial statements. Some additional uses for artificial neural network software in accounting research are also identified.

Originality/value

This paper is the first in the discipline to use artificial neural network software to analyse and compare different texts.

Details

Qualitative Research in Accounting & Management, vol. 5 no. 3
Type: Research Article
ISSN: 1176-6093

Keywords

To view the access options for this content please click here
Article
Publication date: 7 August 2018

Robledo de Almeida Torres Filho, Vanelle Maria da Silva, Lorena Mendes Rodrigues, Paulo Rogério Fontes, Alcinéia de Lemos Souza Ramos and Eduardo Mendes Ramos

The purpose of this paper is to evaluate the classification ability of pork quality by cluster analysis in relation to reference criteria proposed in the literature…

Abstract

Purpose

The purpose of this paper is to evaluate the classification ability of pork quality by cluster analysis in relation to reference criteria proposed in the literature. Verify if clusters were theoretically significant with major pork quality categories. Verify if classificatory parameter values of quality attributes determined “a posteriori” may be used for following categorization.

Design/methodology/approach

In total, 60 pork loins were classified into pale, soft and exudative, reddish-pink, soft and exudative, RFN and dark, firm and dry by reference criteria and hierarchical cluster analyses were performed to identify groups of samples with different attributes, based on only pH45min and on pHu, L* and drip loss.

Findings

Cluster analysis divided total samples into different (p<0.05) smaller groups. Two groups were formed based on only pH45min and five groups were formed based on pHu, L* and drip loss. By these five groups, L* of 44 and 52 distinguished between dark, reddish-pink and pale meat colors and drip loss of 2 and 6 percent distinguished between dry, non-exudative and exudative meats. Cluster analyses identify pork groups with different attributes and the proposed parameters can be used to distinguish between groups theoretically similar to major pork quality categories.

Originality/value

To decide the best destination to pork carcass and to reduce economic losses, the correctly classify of the pork quality is decisive. This study proves that cluster analysis is able to classify pork into groups with significantly different quality attributes, which are significant with major pork quality categories, without unclassified samples.

Details

British Food Journal, vol. 120 no. 7
Type: Research Article
ISSN: 0007-070X

Keywords

To view the access options for this content please click here
Article
Publication date: 1 January 1989

EDIE M. RASMUSSEN and PETER WILLETT

The implementation of hierarchic agglomerative methods of cluster anlaysis for large datasets is very demanding of computational resources when implemented on conventional…

Abstract

The implementation of hierarchic agglomerative methods of cluster anlaysis for large datasets is very demanding of computational resources when implemented on conventional computers. The ICL Distributed Array Processor (DAP) allows many of the scanning and matching operations required in clustering to be carried out in parallel. Experiments are described using the single linkage and Ward's hierarchical agglomerative clustering methods on both real and simulated datasets. Clustering runs on the DAP are compared with the most efficient algorithms currently available implemented on an IBM 3083 BX. The DAP is found to be 2.9–7.9 times as fast as the IBM, the exact degree of speed‐up depending on the size of the dataset, the clustering method, and the serial clustering algorithm that is used. An analysis of the cycle times of the two machines is presented which suggests that further, very substantial speed‐ups could be obtained from array processors of this type if they were to be based on more powerful processing elements.

Details

Journal of Documentation, vol. 45 no. 1
Type: Research Article
ISSN: 0022-0418

To view the access options for this content please click here
Article
Publication date: 1 March 1984

ALAN GRIFFITHS, LESLEY A. ROBINSON and PETER WILLETT

This paper considers the classifications produced by application of the single linkage, complete linkage, group average and Ward clustering methods to the Keen and…

Abstract

This paper considers the classifications produced by application of the single linkage, complete linkage, group average and Ward clustering methods to the Keen and Cranfield document test collections. Experiments were carried out to study the structure of the hierarchies produced by the different methods, the extent to which the methods distort the input similarity matrices during the generation of a classification, and the retrieval effectiveness obtainable in cluster based retrieval. The results would suggest that the single linkage method, which has been used extensively in previous work on document clustering, is not the most effective procedure of those tested, although it should be emphasized that the experiments have used only small document test collections.

Details

Journal of Documentation, vol. 40 no. 3
Type: Research Article
ISSN: 0022-0418

To view the access options for this content please click here
Article
Publication date: 16 December 2019

Muhammad Ahsan Sadiq, Balasundaram Rajeswari and Lubna Ansari

The purpose of the paper is to segment and profile the Indian shoppers in the context of organic foods in India. It proposes to use a healthy lifestyle (HL) as a…

Abstract

Purpose

The purpose of the paper is to segment and profile the Indian shoppers in the context of organic foods in India. It proposes to use a healthy lifestyle (HL) as a segmenting variable and to use a factor-cluster analysis approach to achieve the same. The current study is expected to add a substantial base to the segmentation literature in marketing.

Design/methodology/approach

Food stores in Indian metropolitan city Chennai are sampled, and data is collected in the form of a mall intercept survey method. In total, 441 usable structured questionnaires are filled by the respondents which are subjected to suitable statistical analysis.

Findings

Three significantly different consumer segments emerged from the given sample of respondents, which shows uniqueness concerning consumer’s, HL features, demographics and the variables of the theory of planned behavior (TPB).

Research limitations/implications

Clustering method used to segment the potential shoppers of organic foods is an exploratory technique only. It cannot be treated or generalized to the population like those of inferential techniques. The researcher suggested testing the same with a larger sample size and in a different context. It is limited to urban and suburban facets of the metropolitan city in India.

Originality/value

The study will be helpful to marketers and decision makers to target the potential organic foods consumers.

Details

South Asian Journal of Business Studies, vol. 9 no. 2
Type: Research Article
ISSN: 2398-628X

Keywords

To view the access options for this content please click here
Article
Publication date: 25 August 2020

Matthew Q. McPherson, Daniel Friesner and Carl S. Bozman

Community asset mapping (CAM) is an evidence-based activity commonly used in local socioeconomic development initiatives. Residents and other stakeholders collaboratively…

Abstract

Purpose

Community asset mapping (CAM) is an evidence-based activity commonly used in local socioeconomic development initiatives. Residents and other stakeholders collaboratively identify the resources that they deem most important to the vitality of their community. Results are depicted qualitatively using maps. While maps are a useful means to convey information, alternate approaches to summarize data drawn from CAM activities may yield additional inferences that better inform community development initiatives.

Design/methodology/approach

This study conducted a retrospective analysis of secondary, de-identified data collected from the 2015–2016 Gonzaga University Logan Neighborhood Asset Mapping Project. Hierarchical and nonhierarchical cluster analyses were used to establish interrelationships between the perceived importance of various community assets.

Findings

The hierarchical cluster analysis revealed a very intuitive hierarchical clustering of community assets, with various health care services tightly clustered together. Similarly, farmers’ markets, community gardens and meeting spaces were clustered closely together. Third, community education and care services for all age groups were clustered together. The nonhierarchical cluster analysis revealed intuitive clustering of respondent groups who valued particular sets of assets.

Originality/value

By identifying these clusters and characterizing the linkages between them, it is possible to fund multiple development initiatives that are mutually reinforcing. For example, if the neighborhood obtains funds to invest, then they could be used to facilitate both community gardens and farmers’ markets, two closely related activities. Additional physical locations might also be developed to support (possibly outdoor) meeting space.

Peer review

The peer review history for this article is available at: https://publons.com/publon/10.1108/IJSE-04-2020-0206.

Details

International Journal of Social Economics, vol. 47 no. 10
Type: Research Article
ISSN: 0306-8293

Keywords

To view the access options for this content please click here
Article
Publication date: 19 September 2008

George Menexes and Stamatis Angelopoulos

The aim of the study is to propose certain agricultural policy measures for the financing and development of Greek farms, established by young farmers, based on the…

Abstract

Purpose

The aim of the study is to propose certain agricultural policy measures for the financing and development of Greek farms, established by young farmers, based on the results of a clustering method suitable for handling socio‐economic categorical data.

Design/methodology/approach

The clustering method was applied to categorical data collected from 110 randomly selected investment plans of Greek agricultural farms. The investment plans were submitted to the “Region of Central Macedonia” administrative office, in the framework of the Operational Programme “Agricultural Development – Reform of the Countryside 2000‐2006” and refer to agricultural investments by “Young Farmers”, according to the terms and conditions of Priority Axis III: “Improvement of the Age Composition of the Agricultural Population”. The input variables for the analyses were the farmers' gender, age class, education level and permanent place of residence, the farms' agricultural activity, Human Labour Units (HLU) and farms' viability level. All these variables were measured on nominal or ordinal scales. The available data were analyzed by means of a hierarchical cluster analysis method applied on the rows of an appropriate matrix of a complete disjunctive form with a dummy coding 0 or 1. The similarities were measured through the Benzécri'sχ2distance (metric), while the Ward's method was used as a criterion for cluster formation.

Findings

Five clusters of farms emerged, with statistically significant diverse socio‐economic profiles. The most important impact on the formation of the groups of farms was found to be related to the number of HLU, the farmers' level of education and gender. This derived typology allows for the determination of a flexible development and funding policy for the agricultural farms, based on the socio‐economic profile of the formulated clusters.

Research limitations/implications

One of the limitations of the current study derives from the fact that the clustering method used is suitable only for categorical, non‐metric data. Another limitation comes from the fact that a relative small number of investment plans were used in the analysis. A larger sample covering and other geographical regions is needed in order to confirm the current results and make nation‐wide comparisons and “tailor‐made” proposals for financing and development. Finally, it is interesting to contact longitudinal surveys in order to evaluate the effectiveness of the funding policy of the corresponding programme.

Originality/value

The study's results could be useful to practitioners and academics because certain agricultural policy measures for the financing and development of Greek farms established by young farmers are proposed. Additionally, the data analysis method used in this study offers an alternative way for clustering categorical data.

Details

EuroMed Journal of Business, vol. 3 no. 3
Type: Research Article
ISSN: 1450-2194

Keywords

To view the access options for this content please click here
Article
Publication date: 12 January 2010

Marko Kohtamäki

Relationship learning is a topic of considerable importance for industrial networks, yet a lack of empirical research on the impact of relationship governance structures…

Abstract

Purpose

Relationship learning is a topic of considerable importance for industrial networks, yet a lack of empirical research on the impact of relationship governance structures on relationship learning remains. The purpose of this paper is to analyze the impact of relationship governance structures on learning in partnerships.

Design/methodology/approach

This paper contributes to the closure of the research gap by examining sample data drawn from 42 interviews on the subject of 199 customer‐supplier relationships within the Finnish metal and electronics industries. As a method, the paper applies cluster analysis and analysis of variance mean‐comparison.

Findings

The results of this paper show that balanced hybrid governance structures explain learning in partnerships, which suggests that certain combinations of relationship governance mechanisms (price, hierarchical, and social mechanism) produce the best learning outcomes in partnerships. Results suggest that managers should use hybrid relationship governance structures when governing their supplier partnerships.

Research limitations/implications

The paper has some limitations such as limited sample size, cross‐sectional data, and difficulties due to measuring social phenomenon such as learning. Owing to the interview method being applied, research is bound to apply a sample data drawn from companies that operate in the west coast in Finland. These limitations need to be considered when applying the results.

Practical implications

The results encourage managers to use different governance mechanisms simultaneously when managing their company's supply chain partnerships. The result emphasizes the role of active relationship management.

Originality/value

The paper is one of the first to empirically show that relationship learning is best facilitated by using various relationship governance mechanisms simultaneously. Trust needs to be complemented by hierarchical and possibly by price mechanism.

Details

The Learning Organization, vol. 17 no. 1
Type: Research Article
ISSN: 0969-6474

Keywords

1 – 10 of over 9000