Abstract
In this research, we will investigate several different approaches and methods to displaying multivariate data. Emphasis will be placed on end-user-customization tools and flexibility in dynamic and interactive displays. Specifically, we will highlight the use of motion charts using Markus Gesmann’s googleVis package in R. We will demonstrate the visualization of time-series data and also the results of multidimensional scaling and principal component analysis using this tool. The goals of these displays are ease of usability and interpretation, dynamic customization options, and the ability to display multivariate data in a meaningful way. In addition we will explore partial least squares path modeling using data collected from the Knight Foundation and Gallup during the years 2008–2010 to illustrate the attachment of people to their communities in a new and innovative way.
Similar content being viewed by others
References
Everitt B, Dunn G (2001) Applied multivariate data analysis. Hodder Arnold, London
Gesmann M, de Castillo D (2011) Using the Google Visualization API with R. R J 3(2):40–44
Hofmann H, Wickham H, Cook D (2019) The 2013 Data Expo of the American Statistical Association, Computational Statistics XX(YY):This Issue
Husson F, Josse J, Le S, Mazet J (2013) R package version 1.24. http://CRAN.R-project.org/package=FactoMineR
Knight Foundation Soul of the Community (2013) What attaches people to their communities? http://www.soulofthecommunity.org/
R Core Team (2013) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org/
Sanchez G (2013) PLS Path Modeling with R. Trowchez Editions. Berkeley, 2013. http://www.gastonsanchez.com/PLSPathModelingwithR.pdf
Wickham H (2009) ggplot2: elegant graphics for data analysis. Springer, New York
Acknowledgements
The author greatly appreciates the generous comments and suggestions of two anonymous reviewers on the first version of this article.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Tables 6, 7, 8, 9 show the loadings from the MDS.
Hierarchical Cluster Analysis seeks to create clusters based on sets of dissimilarities for the cities. Through the use of an iterative algorithm, hierarchical cluster analysis begins with each city in their own cluster, and then joins the cities together that are the most similar. Figure 16 shows the dendrograms for each year, and the clusters of cities obtained by this method. Cutting each tree at 0.8, we can observe different numbers of clusters for each year, as well as different groupings of the cities throughout time.
Rights and permissions
About this article
Cite this article
Orth, J.M. Drivers of community attachment: an interactive analysis. Comput Stat 34, 1591–1611 (2019). https://doi.org/10.1007/s00180-018-00862-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-018-00862-y