Predictions from Ordinal Clinical Data (450 Patients)

Abstract

In Chap. 9 the typology of medical data was reviewed. Ordinal data are, like nominal data (Chap. 10), discrete data, however, with a stepping pattern, like severity scores, intelligence levels, physical strength scores. They are usually assessed with frequency tables and bar charts. Unlike scale data, that also have a stepping pattern, they do not necessarily have to have steps with equal intervals. Statistical testing is not of much interest. Statistical testing becomes, however, interesting, if we want to know whether two ordinal variables like levels of satisfaction with treatment and treatment outcome are differently distributed between one another. An interaction matrix of these two ordinal variables could then be used to test whether one treatment level performs better than the other. We should add that sometimes an ordinal variable can very well be analyzed as a nominal one (e.g., treatment outcome in the current Chapter and in Chap. 10).

Electronic Supplementary Material(s)

q-q plots (SAV 1 kb)