Multidimensional Scaling and Correspondence Analysis

2018 ◽  
pp. 267-293
Author(s):  
Kimmo Vehkalahti ◽  
Brian S. Everitt
Keyword(s):  
Multidimensional Scaling ◽  
Correspondence Analysis

scholarly journals Textual Data Science for Logistics and Supply Chain Management

Logistics ◽  
2021 ◽  
Vol 5 (3) ◽  
pp. 56
Author(s):  
Horst Treiblmaier ◽  
Patrick Mair
Keyword(s):  
Supply Chain ◽  
Supply Chain Management ◽  
Multidimensional Scaling ◽  
Sentiment Analysis ◽  
Correspondence Analysis ◽  
Data Science ◽  
Topic Models ◽  
Chain Management ◽  
Word Clouds ◽  
Textual Data

Background: Researchers in logistics and supply chain management apply a multitude of methods. So far, however, the potential of textual data science has not been fully exploited to automatically analyze large chunks of textual data and to extract relevant insights. Methods: In this paper, we use data from 19 qualitative interviews with supply chain experts and illustrate how the following methods can be applied: (1) word clouds, (2) sentiment analysis, (3) topic models, (4) correspondence analysis, and (5) multidimensional scaling. Results: Word clouds show the most frequent words in a body of text. Sentiment analysis can be used to calculate polarity scores based on the sentiments that the respondents had in their interviews. Topic models cluster the texts based on dominating topics. Correspondence analysis shows the associations between the words being used and the respective managers. Multidimensional scaling allows researchers to visualize the similarities between the interviews and yields clusters of managers, which can also be used to highlight differences between companies. Conclusions: Textual data science can be applied to mine qualitative data and to extract novel knowledge. This can yield interesting insights that can supplement existing research approaches in logistics and supply chain research.

PUBLIC TRANSPORT IMAGE POSITIONING USING MULTIDIMENSIONAL SCALING AND CORRESPONDENCE ANALYSIS

2016 ◽  
Vol 78 (12-3) ◽  
Author(s):  
Zamalia Mahmud ◽  
Nor Hidayah Hassim
Keyword(s):  
Service Quality ◽  
Multidimensional Scaling ◽  
Correspondence Analysis ◽  
Public Transport ◽  
Public Transportation ◽  
Strong Association ◽  
Perceptual Maps ◽  
Klang Valley ◽  
Convenience Sampling ◽  
Comfortable Ride

There is still a great demand for public transportation in Malaysia and express buses are no exception. In order to stay competitive, bus companies must position their image and provide a better service for their customers. This study is intended to identify the position of express buses based on customers’ satisfaction towards the service quality by using Multidimensional Scaling (MDS) and Correspondence Analysis (CA). It is also intended to identify the presence or availability of the services/features/appearances provided by the bus company. Data were collected from 142 passengers using convenience sampling at an undisclosed Express Bus Terminal in Klang Valley. The bus companies included in this study were SExpress, KTB, MExpress, MahExpress, DExpress and CExpress. Multidimensional scaling was used to compare the position of the express buses based on the customers’ satisfaction towards the service quality while correspondence analysis was used to investigate the presence or availability of the services/features/appearances provided by the bus company. Results of the analysis show that KTB has the best performance in terms of its responsiveness and assurance in the service quality whereas SExpress has strong association with empathy service quality. MahExpress performed comparatively well on the tangible service quality. MahExpress is associated with “on board entertainment” and “comfortable ride” whereas MExpress is associated with “more leg space in the bus”. SExpress and KTB are highly competitive because passengers in the cluster perceived similar services/features regarding “driver informs passengers when the bus arrives at respective bus stations” and “bus has comfortable seats”. In conclusion, both methods have created perceptual maps that illustrate the product positions and their attributes which is important to facilitate marketing of the products and services.

Plant communities structure and composition in three coastal wetlands in southern Apulia (Italy)

Biologia ◽  
2011 ◽  
Vol 66 (6) ◽  
Author(s):  
Valeria Tomaselli ◽  
Romeo Pietro ◽  
Saverio Sciandrello
Keyword(s):  
Multidimensional Scaling ◽  
Plant Communities ◽  
Correspondence Analysis ◽  
Coastal Wetlands ◽  
Detrended Correspondence Analysis ◽  
Sandy Soils ◽  
Coastal Areas ◽  
New Associations ◽  
Ephemeral Plant ◽  
Similarity Ratio

AbstractIn this paper the results of a study on the composition and the distribution of the plant communities in three coastal areas of southern Apulia are presented. A total of about 180 vegetation relevés were performed following the Braun-Blanquet phytosociological method. Vegetation data were analysed using both classification (UPGMA, similarity ratio) and ordination methods (including Non-metric Multidimensional Scaling (NMS) and Detrended Correspondence Analysis (DCA). The relevés are distributed in the following classes: Molinio-Arrhenateretea, Phragmito-Magnocaricetea, Juncetea maritimi, Sarcocornietea fruticosae, Saginetea maritimae, Thero-Salicornietea, Helianthemetea guttati. Detailed information about structure and zoning of the detected plant communities are here provided. Two new associations, belonging to the Alkanno-Maresion nanae alliance (microphytic ephemeral plant communities growing on sandy soils, Helianthemetea guttati class) have been described here, both in the “Torre Guaceto” site. The area of “Le Cesine” showed the highest total number of plant communities, while the “Saline di Punta della Contessa” site revealed the largest number of Sarcocornietea fruticosae plant communities.

scholarly journals Métodos Quantitativos Interpretativos na Educação em Ciências: Abordagens para Análise Multivariada de Dados

2019 ◽  
pp. 775-800
Author(s):  
Matheus Monteiro Nascimento ◽  
Estevão Antunes Júnior ◽  
Cláudio Cavalcanti ◽  
Fernanda Ostermann
Keyword(s):  
Multidimensional Scaling ◽  
Correspondence Analysis ◽  
De Se

A área de pesquisa em Educação em Ciências ainda sofre influências do positivismo, materializadas no delineamento de estudos tanto quantitativos como qualitativos. Os métodos quantitativos tradicionais se mostram como fortes agentes da perspectiva positivista de pesquisa, principalmente pela ingênua interpretação de que os dados numéricos representam a realidade dos fatos. Na intenção de se afastar dessa visão, observou-se um avanço na direção do desenvolvimento dos chamados métodos mistos, principalmente quanto à análise quantitativa interpretativa, que incentiva uma variedade maior de métodos analíticos para poder melhor compreender o objeto de estudo. Assim, objetiva-se discutir, nesse artigo, o Escalonamento Multidimensional (Multidimensional Scaling - EMD) e a Análise de Correspondência (Correspondence Analysis - AC), que se configuram como possibilidades de métodos quantitativos interpretativos recorrentemente utilizados na análise multivariada de dados, além de apresentar exemplos de aplicação em pesquisas na área de Educação em Ciências. O resultado da nossa apresentação é que métodos quantitativos interpretativos devidamente fundamentados e refletidos podem se afastar do paradigma positivista que ainda permeia a área de Educação em Ciências.

Sign in / Sign up

Export Citation Format

Share Document