 # Types of Variables and levels of Data

Nominal (non-parametric) data, this data uses numbers to label categories. This numbers cannot be used to calculate any statistic quantity. Example is when its used in gender to label female as 1 and male as 2.

Ordinal (non-parametric) data uses numbers to define the order of performance; data is ranked but not measured in any scientific manner. Therefore, it cannot be used to calculate any statistics such as mean.

Interval (parametric) data is data whose difference between consecutive numbers is equal. Example is distance, time and speed i.e. the difference between 3&4 is equal to the difference between 23&24.

Ratio (parametric) data is like interval data with an absolute zero, a score of 40 is considered twice as good as a score of 20.

Independent variables are variables whose variation does not depend on that of other variables i.e. a variable that stands alone and is not changed by the behavior of other variables. Examples include a person’s age because a factor such as place of residence does not change it.

A dependent variable is exactly the opposite of independent variable.  It is a variable that depend on other factors. For example, the results of students depend on the amount of time spent studying.

A categorical variable (sometimes called a nominal variable nominal variable) is one that has two or more categories, but there is no basic ordering to the categories. For example the variable gender has two categories (male and female) but there is no intrinsic (i.e. there is no agreed way to order these categories from highest to lowest) ordering to the categories.

An ordinal variable is similar to a categorical variable but there is a clear ordering of the categories in the ordinal case i.e. in addition to grouping variables into categories you can further classify variables in these categories as low, medium and high.

An interval variable is similar to an ordinal variable, except that the intervals between the values of the intervals are equally spaced.

It is important to first identify whether a variable is categorical, ordinal or interval. For example, it would not make sense to compute the average of gender. An average of a categorical variable will not make much sense because there is no fundamental ordering of the levels.