It is a commonplace to view  Correspondence Analysis  (CA)  as "Bourdieu's statististical method": rightly so, since Bourdieu's work has provided an exemplary use of CA.  In fact, beyond CA, a constant  concern for Bourdieu has been  to  substantiate his  theories  by statistical  data  and analyses.  This essential aspect of Bourdieu' work  has not  been   covered in detail so far by those who have written about Bourdieu' theories . Hereafter are some landmarks, from traditional statistics to Geometric Data Analysis. 

First period (1960s and early 1970s): Bourdieu before Correspondence Analysis  
   As early as the "Algerian times" (1958-1961),  Bourdieu cooperated with statisticians of INSEE  (the French national  Institute of official statistics). The collaboration continued in the 1960s, as reflected in  the contribution to Les Héritiers   (1964) by Alain Darbel, who calculated the  epoch-making  "chances of access to university" for the various social categories.  The books of this period are filled with contingency tables,  often  with traditional chi-square statistics.

Second period (mid-1970s): Correspondence analysis
In  the early 1970s, Bourdieu elaborated  the concept of  field; and at the same time  he was becoming  aware of  the shortcomings of the traditional statistical tools: `` The particular relations between a dependent variable (political opinion) and so-called independent variables such as sex,  age and religion, tend to dissimulate the complete system of relations that make up the true principle of the force and    form   specific to the effects recorded in such and such particular correlation." ( La Distinction , 1979, p.103).
Meanwhile, the geometric approach developed by Jean-Paul Benzécri  and his associates around Correspondence Analysis was emerging. Encouraged by his braintrust of mathematicians, and helped by Salah  Bouhedja (a programmer trained in the geometric  methods), Bourdieu turned to the new approach to synthetize   his data and sustantiate his multidimensional model of social space. ``I use Correspondence Analysis very much, because I think that it is essentially a relational procedure whose philosophy fully expresses what in my view constitutes social reality. It is a procedure that 'thinks' in relations, as I try to do it with the concept of field.'' (Preface of the German edition of Le Métier de Sociologue , 1991). 

Third period (from the late 1970s): Multiple Correspondence Analysis
A breakthrough  in  Geometric Data Analysis was accomplished when the basic algorithm  of Correspondence Analysis was applied  to Individuals x Variables tables, synthetizing a host of contingency tables by the two fundamental clouds of properties and of individuals. This approach was used by  Bourdieu and Saint-Martin in the pioneer paper Anatomie du Goût  (1976) taken up in La Distinction (1979). More specifically, for categorized variables, Multiple Correspondence Analysis (MCA)  became  in France a standard method  for the analysis of questionnaires.  This method was applied in  Le patronat (1978),  Homo Academicus, Noblesse d'Etat,  Structures sociales de l'économie, etc.  Up to now, MCA  has come to be part of all empirical   work conducted along Bourdieusian  lines.  In this last lecture at College de France, in 2001, Bourdieu reiterated: 

``Those who know  the principles of multiple correspondence analysis will grasp the affinities between this method of mathematical analysis  and the thinking in terms of field. "  (in Science  de la science et réflexivité , p.70,  2001).

References
  . Rouanet H., Ackermann W., Le Roux B.  (2000) . The geometric analysis of questionnaires: the lesson of Bourdieu's La Distinction,  Bulletin de Méthodologie Sociologique , 65, 5-15.
  . Bourdieu P. (1999). Une révolution conservatrice dans l'édition, Actes de la Recherche  en Sciences Sociales [The last Bourdieu's empirical study]
  .  Hjellbrekke J.,  Le Roux B., Korsnes O., Lebaron F., Rosenlund L., Rouanet H. (2007) : The Norwegian field of power, European Societies .
  . Lebaron F. ( 2006). L'enquête quantitative : recueil et analyse des données, Paris, Dunod.

Module Analyse  Géométrique des données