What is quantitative data?

Quantitative data is data you can count or measure—numeric information like age, revenue, or time. It deals in concrete facts: if someone is 85, you can’t argue that they’re 37.

Because it’s numeric, math usually plays a role in expressing a quantitative result. If you’re tracking 100 people and 20 are 85 years old, 20% of your participants are 85 years old.

[Embed: 1QRx4m3axKbEtdiGslIn1K]

Types of quantitative data

Quantitative data is anything you can measure in definite units and numbers. There are many examples of quantitative data, including:

Revenue in dollars
Website page load speed
Time in seconds, minutes, or hours
Distance in miles or kilometers
The results of a data-driven experiment
Age in months or years

Quantitative data: Collection methods

You can collect quantitative data through surveys. For instance, you could send out a survey about the average income in the households of Tulsa, Oklahoma, among a group of 500 people.

You’d be collecting quantitative data because salaries are inherently measurable.

There are quite a few quantitative data collection methods, including:

Archival reviews
In-app behavior data
Analytics

An example of quantitative data in action

Structured observations are an exceptionally immersive method that can give you insights into a certain situation. For example, if you want to study how long the average school student’s screen time is, you need to create an accurate .

First, figure out by which grade most students have cell phones. You’ll need permission to collect screen time data from a statistically relevant sample size of each grade.

You’d then set a timeline for the experiment. It’s best to run this during a typical week, since a big game, prom, or other events could skew your data.

Once your participants have shared their screen time data with you, it’s time to analyze the results. To pull all the data into one place for analysis, you might want to involve a developer to extract the data.

Visual representations such as graphs and pie charts are common ways to share results. A developer can create these with coding languages such as R or Python. If a developer isn’t on hand, you can use manual data entry to pull each participant’s data into one spreadsheet.

Once you’ve analyzed the data, you get to share the results. When you’re reporting the stats, remember that quantitative data is purely factual—avoid generalizations and err on the side of caution.

Too general, opinion-based: “Students at my school spend most of their time on their phones.”

Much better at sticking to the facts: “70% of students in grades 8–12 at Academy X averaged four hours of screen time per day during the week of the study.”

Quantitative data in UX design

People in STEM (science, technology, engineering, and mathematics) regularly use quantitative data. It answers the following questions:

What?
How many?
How often?

This form of data is quite beneficial for businesses and marketing. In relation to , , or software engineering, quantitative data can refer to:

The rate of as a percentage of website visitors
Conversions
Page load speed
In-app behaviors and the percentage of users doing what behaviors
Demographics and the percentage of users that hold each characteristic
CAC (customer acquisition cost)

Quantitative data helps you keep track of your bottom line as a business. It makes it easier to stay on top of what’s happening across the board.

Quantitative data analysis methods

There are many ways to analyze quantitative data, and the method will likely vary based on your industry and goals.

One example of analyzing quantitative data is Google Analytics. This is especially helpful for anyone who runs a website and wants to measure the following metrics:

The number of people that visited your site in the last day or week
The length of each person’s average session
Where your traffic is coming from

This is only one way to analyze quantitative data, but doing so can be enormously beneficial to your business.

Aside from Google Analytics, you can use many free tools to analyze quantitative data, including:

Excel or Google Sheets
Apache Superset
Looker Studio

Many paid tools with more features also exist, including:

Tableau
GoodData
Looker

Finally, those with programming skills can analyze data using programming languages such as:

Python
R
SQL

Advantages of quantitative data

A huge advantage of using quantitative data is that you’re presenting facts. As long as you’ve triple-checked your calculations to eliminate any errors, it’s a reliable way to prove a point.

Numbers don’t lie. If a notebook is flying off the shelves and you’ve sold $23,000 in stock over the past three months, that suggests it would make sense to invest in more of these notebooks.

You could propose this to your team using irrefutable quantitative data and hopefully increase your business’s revenue as a result.

Discrete and continuous data

There are two types of quantitative data: .

Discrete quantitative data is fixed-value information that you collect at a given time. It cares less about what happens over time and more about what percentage exists or the number at a specific point.

On the other hand, you measure continuous data across a period.

Discrete quantitative data

Examples include:

An adult’s shoe size
The number of players on a team
The number of employees at a company

These values are fixed counts, not measurements that shift along a scale. You don’t measure discrete data over time because it only covers information for a specific event. For example, if a team has 12 players on its roster one season, that’s discrete data. It might have 13 or 14 the next season, but you’re only counting one season, so that’s what matters.

Pie charts and bar graphs are usually the most effective way to represent discrete quantitative data.

Continuous quantitative data

Examples include:

Website traffic
Water temperature
The time it takes to complete a task
Wind speed

Maybe a product team has just introduced a new and highly requested feature and wants to measure how this has influenced the conversion rate. Here, we can take measurements from before the feature launched and continually measure the post-launch to see if it grows. This is an example of continuous quantitative data.

Line graphs are generally the most effective way to express continuous quantitative data.

There are two subcategories of continuous data: Interval data and ratio data.

Interval data

is data that you can measure along a continuum. Temperature is one example because it moves above and below zero.

Interval data is always numerical, with a standardized, equal distance between any two adjacent points on the scale—the gap between 10 and 20 degrees is the same as the gap between 20 and 30. What it lacks is a true zero point.

Ratio data

Ratio data is quite similar to interval data. The only difference is that it has a true zero. As we noted, temperature readings can be accurate below zero. But there’s no such thing as −1 lbs, so a scale uses ratio data—it starts at 0.0 and can’t go any lower.

Weight, length, height, and concentration are all examples of ratio data.

Quantitative versus qualitative data

In very simple terms, quantitative data refers to quantities, while qualitative data refers to qualities.

Quantitative data refers to statistics, numbers, and measurements.

refers to descriptions of people, places, and things—it describes specific attributes such as blue eyes or red flowers. Colors are qualitative data because they describe someone or something.

For instance, you can conduct a quantitative survey measuring the number of Republicans and the number of Democrats residing in a particular state. To understand why they vote for a party, you’d have to gather qualitative data, such as their ideals, religions, motivations, and life experiences.

What is the difference between quantitative and qualitative data?

The primary is this: Quantitative data is a fact. If someone has earned $100,000 in the last 12 months, that’s an inarguable fact, not an opinion.

On the other hand, why someone supports a political party is qualitative: their reasoning rests on values and beliefs people can argue about, and both sides can have solid points. The only irrefutable facts come from quantitative data.

Should you use qualitative or quantitative data for your research?

The simplest way to answer this question is to work out exactly what questions you’re trying to answer. Do you need to know the “what” or the “why”?

Often in the digital product space, companies already have existing in-app behavior data and can likely answer the “what.” But if you don’t know “why” those numbers are what they are, that’s where qualitative data comes in.

Still, this largely depends on the situation at hand: If you’re running a company and want to understand how well a certain product is selling, it makes sense to calculate the number of customer sales over the past week or month using quantitative data.

Gathering will likely work in your favor if you’d like to understand why people aren’t buying a specific product. For instance, if you sell books and you’re struggling to shift a specific title, you might want to ask your customers some qualitative questions:

What genres do you like?
How long do you spend reading each month?
Are there genres you don’t enjoy?

If your store attracts many people who love mystery novels but romance books never sell, you may need to conduct more .

Of course, it will almost always work in your favor to gather qualitative and quantitative data so you can understand the what and the why. This gives you actionable data to address now and an understanding of what products or features your users want for future development.

Quantitative and qualitative data are invaluable in different ways. Crunching concrete numbers helps you understand so much more about your business. And discovering what your customers want through qualitative data gathering makes it more likely that you’ll get it right the first time, saving time and money.