1.2

The Language of Variation: Variables

Variables represent characteristics of data that can change or vary across different observations or measurements.

Variation and Distribution1523% of exam
Understand It
Ace It
Context

What this topic is and why it exists

Variables are properties or characteristics that can assume different values.
In statistics, you need to identify and classify variables accurately to make sense of data.
There are two main categories: categorical and quantitative.
Categorical variables sort data into groups or categories, like eye color or brand preference.
Quantitative variables, on the other hand, measure something numerically, such as height or test scores.
The trap is thinking all numerical data is quantitative.
For example, zip codes are numerical but categorical because they classify regions rather than measure anything.
Misclassifying a variable leads to incorrect analysis and conclusions.
Always consider the context.
Is the number a measurement or a label?
This decision affects which statistical methods you can use.
Confuse them, and you might apply a mean to data where it doesn't make sense or use a chi-square test on data that requires a t-test.
Get this wrong, and your entire analysis could be off from the start.
1 / 9