In business statistics, you run across the idea of variables, which are important mathematical tools for classifying and organizing data. A scale variable, for example, covers a variety of statistical and survey information that can be precisely measured via a numeric value. A nominal variable is a type of scale variable that codes for something that is not quantifiable, such as color, gender or product type.

What Is a Variable?

You can think of a variable as a container that holds data. A variable has a name, a value and a type. For example, for your business sales statistics, you might create a variable called “sales date” that contains the date an item was sold. The variable has a date type that distinguishes it from plain text, dollar amounts and other kinds of data.

Other variables for sales data might include sales amount, product number and customer number.

Why Use Variables?

If you conduct a customer survey and gather, say, three dozen responses, that amount of data is easy to analyze by hand or with a simple Excel spreadsheet. However, if you have large amounts of data and use more sophisticated statistics, variables become useful for organizing the data. When you get into statistical software such as SPSS, MATLAB or SAS, you will also find yourself using variables for number crunching.

Measurement of Variables in Statistics

Variables are helpful when you need to evaluate large amounts of raw statistical data. You may, for example, have a series of numbers that represent the age of people that have answered a survey. By assigning a variable to the series and calling the variable “age,” you give the numbers meaning. The age variable can take on actual values, such as 11, 21, 19 or 57.

By applying various kinds of mathematical equations to the variables, you can extract meaningful information from the data.

Types of Scale Variables

Scale variables come in four types: nominal, ordinal, interval and ratio. For a nominal variable, values fall into distinct categories, such as political party, color or model number. An ordinal variable handles data that involves order or rank – for example, with the values “first,” “second” or “third”.

Interval variables handle measured quantities, such as weight, height, duration or temperature. Ratio variables measure ratios of quantities, such as the concentration of salt in a water sample or the percent score on a math quiz.

Examples of Nominal Variables

The values of a nominal variable don’t have a relative ranking; one value is not greater than another. They have more to do with general categories, properties or classifications.

For example, a survey of car owners asks for the vehicle’s color. Values for the color variable include red, black, white and silver. Other examples of nominal variables include gender, model number and political affiliation.

Also note that nominal variables don’t take on numeric values such as temperature or speed. Unlike ratio or interval variables, you don’t use them to do arithmetic — just to categorize.

About Likert Scales

A Likert scale is a type of ordinal variable that is widely used in surveys and opinion polls. The variable takes on a limited set of responses that covers a range of possible answers.

For example, if you are asking customers to rate a new flavor of ice cream, you might set up possible responses like “love it,” “like it,” “no opinion,” “dislike” and “strongly dislike.” Note that though a Likert scale is similar to a nominal variable, each response has its place in an ordered list, which is how ordinal variables work.