Classification of Data (HSC SSCE Mathematics Standard): Revision Notes
Classification of Data
Understanding data types
When we collect information, it can take many different forms. If you ask six friends how many pets they own, you might get numbers like , , , , , or . But what if you also record each friend's gender? Then you would get words like male, female, male, female, female, and male. This shows us that not all data consists of numbers.
Data can be divided into two main classifications: categorical data and numerical data. Understanding which type of data you're working with is essential for choosing the right way to analyse and present it.
Why Data Classification Matters
Correctly identifying the type of data you're working with is critical because it determines:
- Which statistical methods you can use
- How you should present your data (graphs, charts, tables)
- What types of calculations are appropriate
- How you interpret your results
Categorical data
Categorical data describes characteristics or qualities rather than quantities. This type of data represents features such as a person's gender, marital status, home address, or favourite type of music.
A Common Misconception
Categorical data can sometimes include numbers (like using '' for unsatisfactory and '' for satisfactory), but these numbers don't have mathematical meaning. You wouldn't add them together or calculate an average, because they're just labels representing categories.
Categorical data has no quantity or amount associated with each category. Instead, it simply groups items into different classifications.
Nominal data
Nominal data uses labels or names that have no particular order or ranking. The categories are simply different from each other, with no category being "higher" or "better" than another.
Examples of Nominal Data
- Gender (classified as 'F' for female or 'M' for male)
- Types of pets (dog, cat, bird, fish)
- Hair colour (blonde, brown, black, red)
- Methods of transport to school (car, bus, train, walk)
Think of the word "nominal" as meaning "name only" – these are just names or labels with no inherent order.
Ordinal data
Ordinal data uses labels or names that indicate a specific order or ranking. While the categories can be arranged in sequence, the difference between categories isn't necessarily equal or measurable.
Examples of Ordinal Data
- Quality ratings (classified as 'A' for excellent, 'B' for good, 'C' for satisfactory)
- Education level (primary school, high school, university)
- Customer satisfaction (very dissatisfied, dissatisfied, neutral, satisfied, very satisfied)
- Competition placing (first, second, third)
Remember: "Ordinal = Order" – both words start with 'Or' to help you remember that ordinal data has a clear sequence.
The key difference between nominal and ordinal data is that ordinal data has a clear sequence or hierarchy (A, B, C shows a progression), while nominal data does not.
Numerical data
Numerical data represents quantities and is used to perform mathematical calculations. When you ask students in your class their height, you expect numerical answers like cm or cm. This type of data allows you to calculate statistics such as averages, totals, and ranges.
Discrete data
Discrete data can only take exact, specific numerical values. These are typically whole numbers that result from counting items or occurrences. You cannot have partial or fractional values between the counts.
Examples of Discrete Data
- The number of sisters someone has (you might have , , or sisters, but not sisters)
- The number of cars in a car park
- The number of students in a classroom
- The number of goals scored in a football match
Key insight: When you count a quantity, you usually generate discrete data. The values are separate and distinct from each other.
Continuous data
Continuous data can take any numerical value within a range, depending on how accurately you measure it. These values typically result from measurements rather than counts, and can include decimals.
Examples of Continuous Data
- A student's height (which might be cm, cm, or any value in between)
- The temperature outside
- The time taken to run a race
- The weight of a package
Key insight: When you measure a quantity, you usually generate continuous data. The values can be infinitely precise, limited only by your measuring instrument.
The Counting vs. Measuring Rule
A simple way to distinguish discrete from continuous data:
- Counting = Discrete (How many? → Exact whole numbers)
- Measuring = Continuous (How much? → Any value depending on precision)
Worked examples
Worked Example 1: Classifying data as categorical or numerical
Let's classify the data from these situations as either categorical or numerical.
a) The heart rate of a group of personal trainers
Heart rate is measured in beats per minute, such as beats per minute. This is a measurement that results in a number that can be used in calculations.
Answer: The heart rate is numerical data.
b) The most watched television show in Australia
A television show has a name, such as "the news" or "Home and Away". This doesn't result in a number; it's a category or label.
Answer: The most watched television show is categorical data.
c) The number of people living in Smith Avenue
The number of people, such as people, can be counted and results in a specific number.
Answer: The number of people living in Smith Avenue is numerical data.
d) The reasons for people travelling to work by train
A reason is a description or category, such as "it is cheaper" or "it is more convenient". This doesn't result in a number.
Answer: The reasons for travelling to work by train is categorical data.
Worked Example 2: Classifying data as nominal or ordinal
Let's classify the following categorical data as nominal or ordinal.
a) School year level
Year level, such as Year , indicates an order or sequence (Year , Year , Year , etc.). However, it doesn't have mathematical meaning in the sense that you wouldn't add or multiply year levels.
Answer: Year level is ordinal data.
b) Internet use at home
Internet use might be categorised by activity, such as email, social media, or online shopping. These are simply labels that don't indicate any particular order or ranking.
Answer: How the internet is used at home is nominal data.
Worked Example 3: Classifying data as discrete or continuous
Let's classify the following numerical data as discrete or continuous.
a) The number of pets in your family
The number of pets is found by counting and must be an exact whole number. You might have , , , or pets, but you cannot have pets.
Answer: The number of pets is discrete data.
b) The perimeter of the school
The perimeter of the school is a measurement of distance. It could be m, m, or m, depending on how accurately you measure. It can take any value within a range.
Answer: The perimeter of the school is continuous data.
Summary of data classification
Here's a quick overview of the complete classification system:
Categorical data – Data classified by the name or label of the category it belongs to
- Nominal data – Labels that do not indicate any order
- Ordinal data – Labels that indicate a specific order or ranking
Numerical data – Data that indicates a quantity and is used to perform calculations
- Discrete data – Data that can only take exact numerical values (usually from counting)
- Continuous data – Data that can take any numerical value (usually from measuring)
Key Points to Remember
-
Categorical data describes qualities or characteristics using labels or categories, while numerical data represents quantities using numbers for calculations.
-
Nominal data has no order (like types of fruit), while ordinal data has a clear sequence (like competition rankings).
-
Discrete data comes from counting and takes exact values only (like the number of students), while continuous data comes from measuring and can take any value (like height or weight).
-
Remember the rule: Counting = Discrete, Measuring = Continuous
-
Even if categorical data uses numbers as labels, those numbers don't have mathematical meaning and shouldn't be used in calculations.