Testing differences in proportions

Abstract

This paper is the sixth in a series of statistics articles recently published by Australian Critical Care. In this paper we explore the most commonly used statistical tests to compare groups of data at the nominal level of measurement. The chosen statistical tests are the chi-square test, chi-square test for goodness of fit, chi-square test for independence, Fisher's exact test, McNemar's test and the use of confidence intervals for proportions. Examples of how to use and interpret the tests are provided.