Getting beyond the surface

Using geometric data analysis in cultural sociology

Authored by: Henk Roose

Routledge International Handbook of the Sociology of Art and Culture

Print publication date:  September  2015
Online publication date:  September  2015

Print ISBN: 9780415855112
eBook ISBN: 9780203740248
Adobe ISBN: 9781135008895

10.4324/9780203740248.ch11

 Download Chapter

 

Abstract

Correspondence analysis is ‘a relational technique of data analysis whose philosophy corresponds exactly to what, in my view, the reality of the social world is. It is a technique which “thinks” in terms of relation, as I try to do precisely with the notion of field’ (Bourdieu and Wacquant 1992: 96). This quotation from the French sociologist Pierre Bourdieu is often invoked as an argument to veer away from traditional correlational techniques like multivariate regression analysis and to opt for Geometric Data Analysis (GDA) as statistical toolbox – away from ‘general linear reality’, which centres on dependent and independent variables with a focus on causality and usually assumes causal attributes to be independent from one another (see Abbott 1988). GDA refers to a group of techniques including for example Correspondence Analysis (CA) that use spatial measures like Euclidean distance and dispersion along principal axes to analyse, describe and visualise large datasets (for good technical introductions and more, see for example Benzécri 1992; Greenacre 2007; Le Roux and Rouanet 2004, 2010; Murtagh 2005; Tenenhaus and Young 1985). Outcomes of GDA are clouds of points in a geometric space – just like numbers are the outcome of standard regression procedures.

 Cite
Search for more...
Back to top

Use of cookies on this website

We are using cookies to provide statistics that help us give you the best experience of our site. You can find out more in our Privacy Policy. By continuing to use the site you are agreeing to our use of cookies.