# Ranked Variable

A ranked variable is an ordinal variable; a variable where every data point can be put in order (1st, 2nd, 3rd, etc.). You may not know an exact value of any of your points, but you know which comes after the other.

## Examples of Ranked Variables

Suppose you ran a satisfaction survey and your respondents ticked a box to show whether they were ‘very unsatisfied’, ‘slightly unsatisfied’ ‘satisfied’ or ‘extremely happy’ with your hotel service. Although none of these responses correspond to an exact numerical value, they can be ordered from least to greatest. The ordinals 1st, 2nd, 3rd, and 4th can be associated with them, so your data is ranked.

Other examples of ranked variables include time-ordered data such as the winners of a race or the order in which flowers emerge, and intensity-ordered data such as the stages of cancer. Popularity rankings for books or music tracks are another form of ranked variable.

## Why Use a Ranked Variable?

Ranked variables are easily collated, easily categorized, and easy to analyse. In general, non paramatic tests designed for them make fewer assumptions than statistical tests for measurement data. That’s why they are often used for survey data, and also why biostatics researchers will often convert measurement data to ranks before running analysis tests.

## Limitations of Ranked Variables

Ranked variables are limited in the amount of information they hold, since differences in ordering doesn’t tell us anything about the degree of difference between categories.

Forgetting this can lead to judgement errors. For instance, suppose a hospital reports the births of five babies born on a certain morning with ordinal variables 1, 2, 3, 4 and 5. One might be tempted to assume that 1 and 4 were born further apart then time-space neighbors 4 and 5, but if the children were born at 6:56, 6:57, 6:58, 6:59 and 10:58 this would not be the case.

These variables are best used in conjunction with other information. While ranked variables are helpful for drawing inferences and analysis, they are less useful for describing conclusions.

## Sources:

------------------------------------------------------------------------------

Need help with a homework or test question? With Chegg Study, you can get step-by-step solutions to your questions from an expert in the field. Your first 30 minutes with a Chegg tutor is free!

Statistical concepts explained visually - Includes many concepts such as sample size, hypothesis tests, or logistic regression, explained by Stephanie Glen, founder of StatisticsHowTo.