Analysis of Categorical Data When Subjects Can Appear in Any Number of Categories

A common item format frequently encountered on survey questionnaires is the one which asks respondents to check all those categories which are personally applicable. Thus, if there are r categories a subject is free to check none, one, or up to r categories. If the researcher wants to compare c inde...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of experimental education 1984-01, Vol.52 (2), p.122-126
Main Authors: Katz, Barry M., Mcsweeney, Maryellen
Format: Article
Language:English
Subjects:
Applied statistics
Associate degrees
Chief executive officers
Hospital administration
Human resources
Medical records
Medication administration
Nurses
Post hoc
Research methods
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A common item format frequently encountered on survey questionnaires is the one which asks respondents to check all those categories which are personally applicable. Thus, if there are r categories a subject is free to check none, one, or up to r categories. If the researcher wants to compare c independent groups on their responses to such an item, the usual chi-square test of homogeneity of distributions is inappropriate since subjects can appear in more than one category of the out-come measure. This paper develops and illustrates a new statistic which can compare the response patterns to the item across groups. Post hoc procedures to be used in conjunction with the statistical test are also developed.
ISSN:0022-0973
1940-0683
DOI:10.1080/00220973.1984.11011880