Qualitative vs. quantitative data: what’s the difference?

No one could possibly read even a small fraction of the information that’s readily available to us. But this abundance of information makes it hard to appreciate what we have at our fingertips. For this, we need a strong sense of when and how each type of information aligns with our research goals.

When gathering or analyzing research, remember not all data is created equal. Taking a step back to analyze the core differences between data types will ultimately lead to better research outcomes. Your hypotheses will become clearer, data collection will improve, and your analysis will be aligned with your inputs and the answers you seek.

Learning the difference between qualitative and quantitative data is an important first step—so where should you start?

A key difference in data is the division between quantitative versus qualitative data. Misunderstanding the difference can lead to interpretive errors and faulty judgments.

In contrast, when you clarify and apply those differences to your own data pool, you’ll have more clarity in your research outcomes and feed into better strategic decision-making.

Understanding the fundamental differences between qualitative and quantitative data is crucial. It helps you hone your research to deliver accurate, reliable outcomes.

Looking at the root origin of the words themselves is a good first step toward mastering these differences.

What is quantitative data?

The exact definition of quantitative is “having quantity” or “measurable.”

Quantitative data is exact and objective. You can express it as a number or measurement. It relates to things like:

• Quantities of things

• Amounts and volumes

• Units of weight and measurements

• Percentage, fractions, and ratios

• Frequencies, rates, or durations

• Test scores

Most of these measurements invoke the idea of formats, like Fahrenheit versus Celsius and miles versus kilometers. The definition of what’s being measured can sometimes come into question. Just because something can be expressed as a number doesn’t mean it is its most appropriate form.

Here’s a good measure of quantitative data: if someone asks “what” is being measured, the answer should be extremely simple, concise, and specific. It shouldn’t leave room for interpretation.

In cases where quantitative data fails to account for other important facts or creates contention over its value, there is likely a degree of ambiguity or subjectivity that hasn’t been explored enough. This is what qualitative data can deliver.

What is qualitative data?

Qualitative data is inherently inexact and subjective. It requires interpretation and value judgments.

The origin meaning of qualitative stems from the Latin word qualitas, meaning “a quality, property, or nature.” It relates to the “possession of qualities without reference to quantities.”

This invokes expressions of meaning and value—but it’s still data. So what does qualitative data represent in practical terms?

It represents the qualities and categories of things. Categorization still requires consistency, so qualitative data doesn’t come at the expense of clarity. It’s flexible, but not without reason. The data must be renewed if a category’s boundaries shift.

Consider the following statement: “The gas station is eight miles away as the crow flies, and we can walk straight there with a gas can.”

This directional information depends on how you interpret it qualitatively. Your interpretation will be subjective and based on context. You’ll make a qualitative assessment or value judgment.

Qualitative data requires a description of the quality of things since it’s linguistic instead of numerical. It invites and even requires, interpretation.

Here are some examples of qualitative data:

• Responses to direct or indirect questions

• Evaluations against a criteria or a set of standards

• Comments

• Reviews

• Opinions or assessments

• Open-ended survey responses

Pure qualitative data alone can be viewed as unrepresentative or inconclusive. It can be less helpful to businesses, which require concrete, actionable items.

When qualitative data reveal answers and insight into the topic you are researching, it should be correlated with quantitative data. This combination will show whether qualitative responses and anecdotes translate into hard, quantifiable numbers.

Whether responses are represented numerically or using descriptive language is a question of methodology. It doesn’t alter the subject under investigation.

Note that qualitative and quantitative data are different tools to address different objectives. The innate value of either type of data depends on context.

If you want to determine value in a quantitative sense, you might use a questionnaire with a rating scale to measure the numerical value consumers rate a product or service. The qualitative value would be the positive impact it delivers on their lives or for their families.

Can a question be both qualitative and quantitative?

Whether you quantify or qualify something often depends on what’s being reflected by that data and the intentions for doing so. Consider the following examples of line-blurring challenges between quantitative and qualitative data:

• What’s the price of a commodity? Is it the price measured in a currency with fluctuating value, such as a USD paper note? Or is it measured to a fixed weight and standard, such as a US-minted $1 silver coin? Is the value fluctuating or fixed? If it’s fluctuating, a fully quantitative measure requires more information (e.g., $X in USD at 12PM on January 1st, 2023).

• What’s the value of a priceless museum artifact? Is it (1) the price the museum paid to obtain it, (2) the market value an experienced appraiser assigns to it, or (3) the experiential value it provides to museum visitors who admire it? The question becomes, which value is being considered? The term “priceless” can be taken literally as a measure of qualitative value, or as a figure of speech meaning “very expensive.”

• What’s the ROI of a park or tree? Is it the amount of real estate, crop, or another commodity that can be obtained using that natural resource? Or is it the emotional and health benefits it provides to people who use and enjoy it?

The same thing can be assigned to both quantitative and qualitative data, depending on who is asking and why. Measures that attempt to take both quantitative and qualitative values into account are possible, but only when the people depending on the data (and what it represents) agree on the terms.

What is quantitative research?

Quantitative research involves:

• Measuring, counting

• Sizing

• Comparing

• Experimenting

• Correlating

• Testing

• Verifying

• Calculating

You can consider this data statistically and scientifically reliable when it’s produced with enough rigor. It’s not open to interpretation unless the researcher breaks the rules and conventions of quantitative data collection and analysis.

This data is essential for statistical analysis, but only when objectively and clearly defined. If this isn’t the case and what is being measured is unclear, the data will be unreliable due to the lack of clearly defined parameters. It doesn’t matter how painstaking or impressive the analysis is.

The robustness of quantitative data relies on having a solid dataset, free from outliers and atypical qualifying factors that reflect the real-world conditions of what you’re trying to measure.

If there’s disagreement over quantitative research’s robustness, it’s likely there are unaddressed questions about what the right thing to measure is and why. This must be thoroughly addressed well before measurement takes place.

What is qualitative research?

In qualitative research, data can be:

• Grouped and themed

• Labeled and coded

• Ranked and ordered

• Compared

• Placed in its overall cultural context

How well it relates to quantitative data is important, but it exists independently of it.

Pure qualitative research must be interpreted. You can use it to categorize what will later be measured quantitatively (e.g., a medical condition’s degrees of severity within a medical research paper, like mild, moderate, or severe). When done well, categories, labels, and groups of data clarify the categories to be analyzed qualitatively, and later measured quantitatively.

Qualitative data can lay the foundation for quantitative analysis by creating defined categories in which to explore data later on. Deciding what category boundaries to set is a judgment call, but the category’s relevance is only as good as the quality of the qualitative research that underpins it.

Researchers need to be fully aware of what’s being measured and how to agree on which type of data to use to address specific research questions. Otherwise, a measure loses meaning because the definition isn’t consistent or categorical. Just as quantitative data is exact, qualitative data should be clearly defined.

Guessing at what quantitative data represents can lead to confusion, as measures don’t relate to real-world operations. It challenges the purpose of previous data collection efforts. When that purpose changes, it offers an opportunity to reevaluate the right type (or category) of data to analyze.

When to use quantitative or qualitative data

It all begins with a decision between quantifying (measurements) or qualifying (interpretations).

A classic example is the difference between hard and soft skills in the workplace. Soft skills are difficult to measure. Hard skills are easy to measure but much less useful.

You should use qualitative data when:

• You have many “why” questions (quantitative methods can address your “what” questions)

• The topic is subjective (e.g., why customers feel a certain way about a brand)

• Quantitative data can’t be of any further use and you’ve learned all you can from it

• You’re no longer clear on what’s being measured by your quantitative data

• Categorizing large amounts of non-contextualized or varied data

• Your measured data is not verifying your hypotheses

• The quantitative data is not lining up with daily realities

• Your organization has too many “data silos”

Quantitative data is most important for:

• Hard, regular, and discrete data points

• Tracking expenses, profits, and other financial matters

• Inventory, product, and supply chain management

• Timing and scheduling

• Keeping tabs on clearly defined KPIs

• Delving deeper into an information category that’s already proven its value to you

• Sizing and prioritizing opportunities or challenges

Don’t be afraid to switch between qualitative and quantitative data. Just be clear when you do.

Benefits and limitations of qualitative and quantitative research

Numbers are not always the be-all and end-all—especially if a definition is not exact or complete. Fortunately, qualitative research’s disadvantages are typically quantitative research’s advantages, and vice versa. Consider their differences, but don’t set them at odds.

Consider the following question as an example: is the value of a workaholic’s time better defined by its impact on their family or their shareholders? Both parties likely have qualitative and quantitative (respectively) standards in mind, as follows:

• Their shareholders consider measurable profits, KPIs, etc.

• Their family considers quality time and the strength of their bond

Each party would consider the value of the workaholic’s time differently, according to their purpose. However, these values can easily be seen as conflicting, prompting any of the three parties to think in one of two modes:

1. Profitability (quantitatively measured)

2. Quality of time (qualitatively measured)

The limitations and benefits of either data type depend on who’s asking. You’ll need to achieve the right balance between these two modes of data analysis to:

1. Demonstrably improve the quality of measurements

2. Naturally, align motives with benchmarks

To get the best answers to your questions, continually review the way you ask them. In the example above, the workaholic could aim to improve the quality of profitable time and the profitability of quality time. This prevents them from seeing hard and soft data as oppositional.

More proactively, data in one category can be used to fill the gaps left by the other category. Today’s apps do just that by synthesizing immense volumes of research data for greater immediate use.

Neither qualitative nor quantitative data alone create the full picture. Used at the right time and for the right reasons, either type of data can offer insight and answers to questions to improve research and wider strategy outcomes.

Favoring quantitative or qualitative data over the other without valid reason risks inaccurate and valueless research. The sky’s the limit when you use them wisely (however much the sky’s edge is open to interpretation…).

Learn more about qualitative research data analysis software