Correspondence analysis
Author:
- 27 October 2014
- book chapter
- Published by John Benjamins Publishing Company
- p. 443-485
Abstract
Correspondence analysis is an exploratory technique for complex categorical data, typical of corpus-driven research. It identifies patterns of association and disassociation in those data. For instance, it can map the correlations between different uses of a linguistic form and its various social and/or morpho-syntactic contexts. The technique presents its results in the form of a two-dimensional plot, which visualises these relationships in an intuitive manner. These plots offer rich representations of the relations between different facets of complex data. Using R, this chapter explains how the technique works and offers a step-by-step explanation of its application and the interpretation of its results. The technique is also compared to the better-known and comparable cluster analysis.Keywords
This publication has 25 references indexed in Scilit:
- A corpus-driven quantitative approach to the construal of Polish thinkPoznan Studies in Contemporary Linguistics, 2012
- Synonyme, lexical fields, and grammatical constructions. A study in usage-based cognitive semantics2010
- Polysemy, syntax, and variation2009
- Simple and Canonical Correspondence Analysis Using theRPackageanacorJournal of Statistical Software, 2009
- going-to-V and gonna-V in child language: A quantitative approach to constructional developmentCognitive Linguistics, 2009
- Usage-based dialectologyAnnual Review of Cognitive Linguistics, 2008
- FactoMineR: AnRPackage for Multivariate AnalysisJournal of Statistical Software, 2008
- The distribution of T/V pronouns in Netherlandic and Belgian Dutch2008
- Theade4Package: Implementing the Duality Diagram for EcologistsJournal of Statistical Software, 2007
- From Simple to Multiple Correspondence Analysis2006