Analysis of Categorical Data

Reference work entry

The analysis of categorical data involves the following methods:


A study of the goodness-of-fit test;


The study of a contingency table and its subsequent analysis, which consists of discovering and studying relationships between the attributes (if they exist);


An homogeneity test of some populations, related to the distribution of a binary qualitative categorical variable;


An examination of the independence hypothesis.


The term “contingency”, used in the relation to cross tables of categorical data was probably first used by Pearson, Karl (1904). The chi-square test, was proposed by Barlett, M.S. in 1937.


See goodness-of-fit and contingency table.



  1. 1.
    Agresti, A.: Categorical Data Analysis. Wiley, New York (1990)zbMATHGoogle Scholar
  2. 2.
    Bartlett, M.S.: Properties of sufficiency and statistical tests. Proc. Roy. Soc. Lond. Ser. A 160, 268–282 (1937)zbMATHCrossRefGoogle Scholar
  3. 3.
    Cox, D.R., Snell, E.J.: Analysis of Binary Data, 2nd edn. Chapman & Hall, London (1990)Google Scholar
  4. 4.
    Haberman, S.J.: Analysis of Qualitative Data. Vol. I: Introductory Topics. Academic, New York (1978)Google Scholar
  5. 5.
    Pearson, K.: On the theory of contingency and its relation to association and normal correlation. Drapers' Company Research Memoirs, Biometric Ser. I., pp. 1–35 (1904)Google Scholar

Copyright information

© Springer-Verlag 2008