Making sense of statistics for family practitioner The "Chi-square test"- getting it right

Abstract

The chi-square test is the most commonly used statistic test for investigating the differences between proportion arising from research. It helps to determine where two or more series of proportions are significantly different from one another or whether a single series of proportions differs from a theoretically expected distribution. In addition it allows us to test whether any observed relationship could simply be due to "chance". Proportions would obviously differ from sample to sample selected simply due to the play of chance. The chi-square test thus assists us in making this judgment in an explicit way, and is a measure of the difference between the proportions observed and those that would have been expected if the null hypothesis of no difference between groups had been true.