You are seeing this message because your Web browser does not support basic Web standards. Find out more about why this message is appearing and what you can do to make your experience on this site better.


ABOUT ARCHIVES
Advanced Search

Welcome   | My Account | E-mail Alerts | Access Rights | Sign In


  Vol. 139 No. 2, February 1985 TABLE OF CONTENTS
  Archives
  •  Online Features
  ARTICLE
 This Article
 •Send to a friend
 • Save in My Folder
 •Save to citation manager
 •Permissions
 Citing Articles
 •Citing articles on HighWire
 •Contact me when this article is cited
 Related Content
 •Similar articles in this journal

Counts, scales, and scores. Levels of observation

G. W. Brown

Description, analysis, and interpretation of biomedical information are guided, in part, by the nature of the observations. Objects or events in categories, ie, nominal data, are simply counted. At a somewhat higher level, observations may have a "more than" character, so they can be ordered or ranked; the increments between the elements may be unknown or not measurable. Interval data have known and fixed increments, but no true zero; ratio scales are interval observations with a true zero. Some relationships between the levels of observation and the presentation and interpretation of biomedical information are discussed.

THIS ARTICLE HAS BEEN CITED BY OTHER ARTICLES

Nonparametric Methods: Clinical Applications
Brown and Hayden
CLIN PEDIATR 1985;24:490-498.
ABSTRACT  





HOME | CURRENT ISSUE | PAST ISSUES | TOPIC COLLECTIONS | SUBMIT | SUBSCRIBE | HELP
CONDITIONS OF USE | PRIVACY POLICY | CONTACT US | SITE MAP
 
© 1985 American Medical Association. All Rights Reserved.