# Variable Types

## Categorical (Qualitative)

### Nominal

Nominal data is comprised of named variables that serve as a category. It has no clear property such as an order or a direction.

Examples include:

• Sports team
• Country
• City

### Ordinal

Ordinal data is categorized in such a way that it contains a natural ordering or direction, but no other attribute.

Examples include:

• A person’s class (Low/Middle/Upper Class)
• Age group
• Review ratings
• Percentages

Note that likert scales also typically fall into this category. Likert scales are typically used on surveys, such as “How do you rate this product? 1: Bad, 2: Average, 3: Good”. Sometimes, likert variables like this are treated as interval data but interval data assumes an equal degree between variables, which is not necessarily reasonable and so this data type should be treated as ordinal.

It is also worth noting that percentages are typically ordinal data. The reason for this is that it will typically be ordinal data at its core. For example a break down of what percentage of people are low, middle and upper class.

## Numerical (Quantitative)

### Discrete

Discrete data is numerical data represented only in whole numbers. It will typically be a count of something.

Examples include:

• Number of products purchased
• Number of toes
• Age (Though can be debated)

### Continuous

Continuous numerical data may be represented by fractions or decimals, it can in principle be broken down indefinitely.

Examples include:

• Height
• Temperature
• Weight
• IQ scores

Continuous data can be further broken down into two sub-categories, interval and ratio.

#### Interval

Interval data is defined by having known differences between measurements, but no clear and natural zero value.

Examples include:

• Temperature
• IQ scores

#### Ratio

Ratio data is defined based on differences between measurements and has a clear and natural zero value.

Examples include:

• Height
• Weight