Types of data
Data is either categorical (labels, like eye colour) or numerical (amounts, like height). Numerical data is discrete if you count it (goals scored) and continuous if you measure it (time in seconds).
Last updated
Analogy
Categorical data is the label on a jar. Numerical data is how much is inside.
Example
Shoe size 9: discreteHeight 172.4 cm: continuousBus route 'X5': categoricalStar rating 1 to 5: ordinal (ordered labels)
In practice
The type of data decides which graph and which test you may use. You cannot average eye colours.
Questions people ask
What is the difference between discrete and continuous data?
Discrete data takes separate values you can count, such as the number of siblings. Continuous data can take any value in a range, such as weight or time, limited only by how precisely you measure. A useful test: if values between two neighbours make sense, the data is continuous.
Is a rating from 1 to 5 stars numerical or categorical?
It is usually called ordinal: categorical data with a natural order. The gap between 4 and 5 stars may not equal the gap between 1 and 2, so averaging is debatable. Many analysts still average ratings, but they should say that they are treating the scale as numerical.