A contingency table is used to show cross-classified categorical data on two or more

variables. The variables can be nominal or ordinal. A nominal variable has cate-

gories with no natural ordering; for example, consider the automotive companies

Ford, General Motors and Toyota. An ordering could be imposed using some crite-

rion like sales, but there is nothing inherent in the categories that makes any particular

ordering obvious. An ordinal variable does have a natural default ordering. For ex-

ample, a disease might be recorded as absent, mild or severe. The five-point Likert

scale ranging through strongly disagree, disagree, neutral, agree and strongly agree

is another example.