Types of Data in Statistics: Definition, Examples & Classification
FREE
Types of Data in Statistics: Definition, Examples & Classification
Before you can analyse a dataset, you must first understand what kind of data you are dealing with. The types of data in statistics determine which calculations are valid, which charts make sense, and which statistical tests you can apply.
In this guide, you will learn the two broad categories of data qualitative and quantitative and the four levels of measurement: nominal, ordinal, interval, and ratio. We will also cover the difference between discrete and continuous data, with plenty of examples to make each concept clear.
If you are new to statistics, you may also want to explore our broader guide on data science statistics before diving deeper.
What is Data in Statistics?
In statistics, data is a collection of facts, figures, observations, or measurements about a group of items or individuals. These facts can be numbers, labels, categories, descriptions, or any other information that can be recorded and analysed.
Data is the raw material of statistical analysis. Before applying formulas or building models, statisticians classify data by type because the same mathematical operation can be meaningful for one type of data and meaningless for another. For example, calculating the average of eye colours is nonsense, but calculating the average height of a group is perfectly valid.
Understanding how data is classified is a foundational skill in statistics and data science. If you are building a career in this field, the Scaler Data Science Course provides a structured path from statistics fundamentals to machine learning.
Transform Your Career
Choose from our industry-leading programs designed for career success
Modern Software and AI Engineering Program
Master full-stack development with AI integration
+1000 moreModern Data Science and ML with specialisation in AI
Advanced data science techniques with AI specialization
+1000 moreAdvanced AIML with Specialisation in Agentic AI
Deep dive into AIML with focus on Agentic systems
+1000 moreDevOps, Cloud & AI Platform Engineering
Build and manage AI-powered cloud infrastructure
+1000 moreAI Engineering Advanced Certification by IIT-Roorkee
Premier AI engineering certification from IIT-Roorkee
Qualitative vs Quantitative Data
The first and most important split in data classification is between qualitative and quantitative data.
Qualitative Data (Categorical Data)
Qualitative data describes qualities or characteristics. It is non-numerical and usually divided into categories.
Examples:
- Eye colour: blue, brown, green
- Blood group: A, B, AB, O
- Gender: male, female, non-binary
- City name: Delhi, Mumbai, Bangalore
- Brand preference: Apple, Samsung, OnePlus
Qualitative data can sometimes be represented by numbers, such as postal codes, but those numbers are only labels and should not be used in arithmetic operations.
Quantitative Data (Numerical Data)
Quantitative data represents amounts or counts and can be expressed as numbers. It supports arithmetic operations such as addition, subtraction, averages, and ratios.
Examples:
- Height in centimetres: 165, 172, 180
- Weight in kilograms: 55, 70, 85
- Number of students in a class: 30, 45, 60
- Temperature in Celsius: 25, 30, 35
- Income in rupees: 50,000, 75,000, 1,00,000
Qualitative vs Quantitative Data Comparison Table
| Feature | Qualitative Data | Quantitative Data |
|---|---|---|
| Also called | Categorical data | Numerical data |
| Nature | Descriptive, attributes | Countable, measurable |
| Examples | Colour, gender, city | Height, weight, income |
| Can you take an average? | No | Yes |
| Suitable charts | Bar chart, pie chart | Histogram, box plot, line chart |
If you are interested in a full overview of descriptive and inferential statistics, see our guide on descriptive and inferential statistics.
Nominal Data
Nominal data is the simplest level of measurement. It consists of categories or labels that have no inherent order or ranking. The values are names, and that is all.
Key properties of nominal data:
- Categories are mutually exclusive
- There is no natural order
- Numbers, if assigned, are only labels
Examples of nominal data:
- Gender: male, female, non-binary
- Blood type: A, B, AB, O
- Hair colour: black, brown, blonde, red
- Marital status: single, married, divorced
- Country codes: IN, US, UK, AU
Allowed operations with nominal data include counting frequencies and calculating the mode. You cannot compute a mean, median, or ratio for nominal data.
Scaler Placement Report and Statistics
Scaler learners achieved 2.5x salary growth with average post-Scaler CTC reaching ₹23L.
Google
Amazon
Microsoft
Flipkart
Adobe1200+ moreOrdinal Data
Ordinal data consists of categories that have a meaningful order or ranking, but the differences between values are not necessarily equal or measurable.
Key properties of ordinal data:
- Categories can be ranked
- The exact difference between ranks is not known or meaningful
- The intervals between values may be unequal
Examples of ordinal data:
- Education level: high school, bachelor’s, master’s, doctorate
- Customer satisfaction: poor, average, good, excellent
- Movie ratings: 1 star, 2 stars, 3 stars, 4 stars, 5 stars
- Class grades: A, B, C, D, F
- Socioeconomic status: low, middle, high
With ordinal data, you can determine the median and percentiles, but you should not assume that the gap between two values is the same everywhere along the scale. For example, the difference between "poor" and "average" may not be the same as between "good" and "excellent."
Interval Data
Interval data is numerical data where the values have a meaningful order and equal intervals between values, but there is no true zero point. Because there is no true zero, ratios are not meaningful.
Key properties of interval data:
- Order matters
- Differences between values are equal and meaningful
- There is no absolute zero
Examples of interval data:
- Temperature in Celsius or Fahrenheit: 20°C, 30°C, 40°C
- Calendar years: 1990, 2000, 2010
- IQ scores: 90, 100, 110
- pH levels: 3, 7, 11
For example, saying that 40°C is twice as hot as 20°C is incorrect because 0°C does not mean the absence of heat. However, saying that 40°C is 20 degrees hotter than 20°C is valid.
Interval data supports operations like addition, subtraction, mean, and standard deviation. It is widely used in inferential statistics and testing, which are covered in descriptive and inferential statistics.
Ratio Data
Ratio data is the highest level of measurement. It has all the properties of interval data plus a true zero point. Because there is a true zero, ratios are meaningful.
Key properties of ratio data:
- Order matters
- Differences between values are equal
- There is a true zero that represents the absence of the quantity
Examples of ratio data:
- Height: 150 cm, 180 cm, 200 cm
- Weight: 50 kg, 70 kg, 100 kg
- Age: 0 years, 25 years, 60 years
- Income: ₹0, ₹50,000, ₹1,00,000
- Distance: 0 km, 10 km, 100 km
Because 0 kg means no weight, it is valid to say that 100 kg is twice as heavy as 50 kg. Ratio data supports all arithmetic operations, including multiplication, division, and ratios.
For a deeper explanation of the four levels of measurement, Scribbr provides a clear and well-respected reference: Scribbr: Levels of Measurement.
Discrete vs Continuous Data
Within quantitative data, there is another important distinction: discrete vs continuous data.
Turn Learning into Career Growth
Discrete Data
Discrete data can only take specific, countable values. There are clear gaps between possible values, usually because the data is based on counting.
Examples:
- Number of students in a classroom: 25, 26, 27
- Number of cars in a parking lot: 10, 11, 12
- Number of goals scored in a match: 0, 1, 2, 3
- Number of defective products in a batch: 0, 1, 2
You cannot have 2.5 students or 1.7 goals. Discrete data is always countable.
Continuous Data
Continuous data can take any value within a given range. It is measured, not counted, and there are infinitely many possible values between any two points.
Examples:
- Height: 165.3 cm, 170.8 cm
- Weight: 55.6 kg, 78.4 kg
- Temperature: 25.5°C, 30.2°C
- Time taken to complete a task: 12.45 seconds, 18.92 seconds
For a practical example of working with numerical data, see our guide on mean, median, and mode.
Levels of Measurement Compared
The four levels of measurement form a hierarchy. Each level adds more mathematical structure than the one before it.
Classification Tree
Data
├── Qualitative (Categorical)
│ ├── Nominal: unordered labels
│ └── Ordinal: ordered categories
│
└── Quantitative (Numerical)
├── Interval: equal gaps, no true zero
├── Ratio: equal gaps, true zero
│
├── Discrete: countable values
└── Continuous: measurable values
Levels of Measurement Comparison Table
| Level | Order | Equal Interval | True Zero | Examples | Allowed Statistics |
|---|---|---|---|---|---|
| Nominal | No | No | No | Gender, blood type, country | Count, frequency, mode |
| Ordinal | Yes | No | No | Ratings, grades, class rank | Median, percentile, rank correlation |
| Interval | Yes | Yes | No | Temperature in °C, IQ score, year | Mean, standard deviation, correlation |
| Ratio | Yes | Yes | Yes | Height, weight, age, income | All operations: mean, ratio, geometric mean |
This table is one of the most useful tools for deciding which statistical methods are appropriate for your data. For example, you can compute the average temperature, but you cannot say that 30°C is twice as hot as 15°C. On the other hand, you can say that a person weighing 80 kg is twice as heavy as a person weighing 40 kg because weight is ratio data.
If you want to apply this knowledge in a professional analytics role, the Scaler Data Analytics Course teaches data handling, visualisation, and statistical analysis with real-world projects.
Conclusion
Classifying data is the first step in any statistical analysis. The main types of data are qualitative and quantitative, which are further divided into four levels of measurement: nominal, ordinal, interval, and ratio. Quantitative data can also be split into discrete and continuous data.
Choosing the right chart, summary statistic, or statistical test depends on the type of data you have. Nominal data can only be counted, ordinal data can be ranked, interval data can be averaged, and ratio data supports all mathematical operations including ratios.
Mastering this classification will make the rest of your statistics and data science journey much easier. To continue learning, explore the Scaler Data Science Course, the Scaler Data Analytics Course, or browse all Scaler courses.
FAQs
Q1. What are the types of data in statistics?
Data in statistics is broadly divided into two types: qualitative and quantitative. Qualitative data describes categories and is further divided into nominal and ordinal data. Quantitative data is numerical and is divided into interval and ratio data. These four sub-types are also called the four levels of measurement. Quantitative data can also be classified as discrete or continuous depending on whether the values are countable or measurable.
Q2. What is the difference between qualitative and quantitative data?
Qualitative data describes qualities, categories, or attributes, such as colour, gender, or brand name. It cannot be used in arithmetic calculations. Quantitative data is numerical and can be measured or counted, such as height, weight, or number of items. It supports arithmetic operations like addition, subtraction, and averaging. The key difference is that qualitative data tells you what category something belongs to, while quantitative data tells you how much or how many.
Q3. What are nominal, ordinal, interval and ratio data?
Nominal data consists of unordered labels, such as gender or blood type. Ordinal data consists of ordered categories, such as ratings or grades, but the gaps between values are not necessarily equal. Interval data has equal intervals but no true zero, such as temperature in Celsius or IQ scores. Ratio data has equal intervals and a true zero, such as height, weight, and age, so ratios like "twice as much" are meaningful.
Q4. What is the difference between discrete and continuous data?
Discrete data consists of countable values with clear gaps between them, such as the number of students in a class or goals scored in a match. Continuous data can take any value within a range and is measured rather than counted, such as height, weight, or temperature. For example, you can have 2 or 3 students, but you cannot have 2.5 students. On the other hand, height can be 165.4 cm or 165.42 cm.
Q5. Why is classifying data important?
Classifying data is important because the data type determines which statistical operations, charts, and tests are valid. You cannot compute the average of nominal data like eye colour, but you can compute the average of ratio data like height. Using the wrong method can lead to meaningless results and incorrect conclusions. Proper classification also helps you choose the right data visualisation and machine learning algorithm.
Q6. Is temperature interval or ratio data?
Temperature in Celsius or Fahrenheit is interval data because the intervals between degrees are equal, but 0°C does not represent the absence of temperature. Ratios are not meaningful, so 40°C is not twice as hot as 20°C. However, temperature in Kelvin is ratio data because 0 K represents absolute zero, the complete absence of thermal energy. Therefore, 200 K is twice as hot as 100 K in a meaningful sense.
