Premium
The analysis of the data for two‐way contingency tables
Author(s) -
Knapp Thomas R.
Publication year - 1999
Publication title -
research in nursing and health
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.836
H-Index - 85
eISSN - 1098-240X
pISSN - 0160-6891
DOI - 10.1002/(sici)1098-240x(199906)22:3<263::aid-nur8>3.0.co;2-p
Subject(s) - guttman scale , contingency table , contingency , a priori and a posteriori , table (database) , scale (ratio) , computer science , statistics , data mining , mathematics , epistemology , philosophy , geography , cartography
One of the best ways, if not the best way, to analyze data displayed in a two‐way contingency table is to use a method originally due to Williams (1952) and later embellished upon by Guttman (1971) and others. This method applies the principles of canonical correlation analysis to contingency table data and obviates the need for the a priori specification of scale values for the two variables whose relationship is explored. In this article the method is described and compared with other approaches, and several examples of its application are provided. © 1999 John Wiley & Sons, Inc. Res Nurs Health 22:263–268, 1999