PSY 350 Lecture Notes - Lecture 2: Parametric Statistics, Categorical Variable, Level Of Measurement
Document Summary
A set of categories that have different names but do not make any quantitative distinctions. Have no natural or logical order to them. A nominal variable with only two categories is called dichotomous. Usually, each observation fits into only one category. We might use numbers to name or refer to the variable (e. g. group 1), even when the underlying variable is really nominal. A set of categories that are organized in an ordered sequence. Some categories are clearly "more than" or "less than" other categories. It tells us about the relative order of the observations. Ordinal data does not tell us how much more than or less than one observation is compared to another. We can do a little more with ordinal data, but most of our statistics need Ordered categories that are all intervals of exactly the same size. Equal differences between numbers on the scale reflect equal distances in magnitude.