EditorialSpecial issue on correspondence analysis and related methods
Section snippets
Correspondence analysis
In “Power transformations in correspondence analysis”, Greenacre (2009) shows two different ways of introducing power transformations into correspondence analysis. Either the original data are powered and then regular CA is performed (with margins that change depending on the transformed data), or the so-called contingency ratios (i.e., observed divided by expected values) are power-transformed and the CA algorithm applied while maintaining the original row and column margins. In the limit as
Methods related to correspondence analysis and principal components analysis
In “Better biplots”, Blasius et al. (2009) discuss different new possibilities of visualizing biplots stemming from principal component analysis. Thereby, the elements of a biplot are a set of axes representing variables that are usually concurrent at the centroid of a set of points representing cases. The axes are approximations to conventional coordinate axes that can be labeled and calibrated. When there are many points, say several thousands, the whole effect can be very confusing. As the
Multidimensional scaling and unfolding methods
In “Trend vector models for the analysis of change in continuous time for multiple groups”, de Rooij (2009) looks at multinomial response data over time, from a modeling perspective. The probability that an individual at a particular time is in a particular group is related inversely to the distance between an individual point and a category point, where these points lie in a low dimensional space. Furthermore, explanatory variables may be available for the individuals at all time points, and
Book reviews
Correspondence analysis and related methods now constitute a wide area of statistical theory and practice. Over the last few years, several books have appeared dealing with these topics. We found it useful to include short reviews of the five most recent books on correspondence analysis and related methods. These reviews may help readers interested in correspondence analysis as regards further reading, be it more application oriented or more statistical and computational. These books, their
Acknowledgements
We would like to thank all of the expert reviewers who helped with selecting the papers in the present issue of CSDA. The initiative to have this special issue arose during the conference Correspondence Analysis and Related Methods 2007, Rotterdam, The Netherlands.
References (20)
- et al.
Better biplots
Computational Statistics and Data Analysis
(2009) Trend vector models for the analysis of change in continuous time for multiple groups
Computational Statistics and Data Analysis
(2009)- et al.
A three-way clusterwise multidimensional unfolding procedure for the spatial representation of context dependent preferences
Computational Statistics and Data Analysis
(2009) Power transformations in correspondence analysis
Computational Statistics and Data Analysis
(2009)- et al.
Non-symmetric correspondence analysis with ordinal variables using orthogonal polynomials
Computational Statistics & Data Analysis
(2007) - et al.
Correspondence analysis approach for finding allele associations in population genetic study
Computational Statistics & Data Analysis
(2007) - et al.
Two types of single-peaked data: Correspondence analysis as an alternative to principal component analysis
Computational Statistics and Data Analysis
(2009) - et al.
Regularized nonsymmetric correspondence analysis
Computational Statistics and Data Analysis
(2009) - et al.
Approximating a similarity matrix by a latent class model: A reappraisal of additive fuzzy clustering
Computational Statistics and Data Analysis
(2009) - et al.
Seriation by constrained correspondence analysis: A simulation study
Computational Statistics and Data Analysis
(2009)
Cited by (15)
Sustainable industries: Production planning and control as an ally to implement strategy
2021, Journal of Cleaner ProductionCitation Excerpt :For each variable, the distance between its categories is reflected in a graph, so that it is possible to analyze the joint graphical representation of a large number of variables and identify similar categories located next to each other; the graphical axles identify the dimensions found in the data (Blasius et al., 2009; Pestana and Gageiro, 2008). The results come from the analysis of visualization of columns and rows of the data table in a usually two-dimensional graphics generated, called map (Blasius and Schmitz, 2015; Blasius et al., 2009; Carvalho, 2004). Due to the standardization used in MCA, the chi-square distance, it can be used to analyze small to large samples (Blasius et al., 2009).
Technology engagement and privacy: A cluster analysis of reported social network use among transport survey respondents
2016, Transportation Research Part C: Emerging TechnologiesCitation Excerpt :Once any groups were identified using HCA, Multi-criteria Analysis (MCA) (Greenacre, 2007) was used to create composite variables for use in the cluster analysis. Several ways of considering MCA exist in the literature (Blasius et al., 2009; Greenacre, 2007). The approach used by SPSS is referred to as homogeneity analysis, and is based on the correlation of the categories chosen for each variable by each respondent (IBM Corporation, 2011; Greenacre, 2007).
Review of rural settlement research based on bibliometric analysis
2023, Frontiers in Environmental ScienceCoffee sensory quality study based on spatial distribution in the Mantiqueira mountain region of Brazil
2020, Journal of Sensory StudiesCorrespondence analysis in practice, third edition
2017, Correspondence Analysis in Practice, Third Edition