Univariate and multivariate analysis of categorial variables

Recent trends in the analysis of categorical or nominal variables were discussed for univariate, multivariate, and psychometric problems. It was shown that several statistical procedures commonly used with these problems have analogues which can be applied to assessing categorical variables. These more general techniques are often required when the data to be analyzed consists of both nominal and interval variables. Even when the data appear to be interval, the investigator can conservatively do an analysis which presumes unordered data. In some cases, the more cautious approach can yield the more meaningful data.