Qualitative vs Quantitative Data — What's the Difference?

What You Will Learn

• The difference between qualitative (categorical) and quantitative (numerical) data
• Sub-types: nominal, ordinal, discrete, continuous
• Why this matters for choosing calculations and charts
• How to classify any column in a dataset in under 10 seconds

Why This Topic Matters

The kind of math you can do depends on the type of data. You can average a column of prices, but averaging a column of cities is meaningless. If you misclassify your data, you will compute nonsense numbers — and worse, you will believe them. This lesson gives you a fast, reliable way to classify any column.

The Simple Idea

Data falls into two big families:

• Qualitative data describes qualities or categories. It answers "what kind?"
• Quantitative data measures quantities or counts. It answers "how much?" or "how many?"

That is the whole distinction. Everything else is a sub-type of one of these two.

Real-World Analogy

Think about a Cricket scorecard. The batter's name, the team, and the dismissal type ("caught", "bowled") are qualitative — they are categories. The runs scored, balls faced, and strike rate are quantitative — they are numbers you can do math on.

Qualitative Data (Categories)

Qualitative data is also called categorical data. There are two flavors:

1. Nominal data

Categories with no natural order. The labels are just labels.

• City: Mumbai, Chennai, Kolkata
• Color: red, blue, green
• Payment method: cash, card, UPI

It does not make sense to say "Mumbai > Chennai". They are just different.

2. Ordinal data

Categories with a natural order, but the gap between them is not measurable.

• T-shirt size: S, M, L, XL
• Education: high school, bachelor's, master's, PhD
• Customer rating: poor, average, good, excellent

You can say "XL > M", but you cannot say "XL is twice as big as M". The gap is not a number.

Quantitative Data (Numbers)

Quantitative data is also called numerical data. It also has two flavors:

1. Discrete data

Numbers that come in whole units — you cannot have a meaningful fraction of them.

• Number of children in a family (you cannot have 2.3 children)
• Number of items in an order
• Number of clicks on a button

2. Continuous data

Numbers that can take any value within a range, including fractions and decimals.

• Height (172.4 cm)
• Temperature (36.6 °C)
• Delivery time in minutes (28.7 min)
• Price (₹499.95)

Quick Classification Table

* Some analysts treat 1–5 star ratings as quantitative because the gap between 1 and 2 "feels" similar to the gap between 4 and 5. The honest answer: it depends on context. Treat as ordinal unless you are sure the gaps are equal.
** Age is technically continuous (you can be 24.6 years old) but usually recorded in whole years, so in practice it often behaves as discrete.

Why This Classification Matters

Notice the "No" entries. Averaging a column of cities gives you a number, but that number is meaningless. Excel will not stop you. SQL will not stop you. You have to stop yourself.

Step-by-Step: How to Classify Any Column

Ask these three questions in order:

1. Is it a number? If no → Qualitative. If yes → go to step 2.
2. Does the number measure an amount or count? If no (e.g., phone number, pin code, year as a label), it is actually qualitative stored as a number. If yes → Quantitative.
3. If quantitative: Can it be a fraction? Yes → Continuous. No → Discrete.

Worked example

A column called pin_code contains 560001, 600001, 700001. Is it quantitative?

No. Pin codes look like numbers, but they are labels. Averaging pin codes is nonsense. They are nominal qualitative data stored as numbers. This is one of the most common beginner mistakes.

Common Mistakes

1. Averaging categorical data. Especially pin codes, phone numbers, and IDs stored as numbers.
2. Treating ordinal data as if intervals are equal. A 1→2 jump in satisfaction is not necessarily the same as a 4→5 jump.
3. Forgetting that "yes/no" is data. Boolean fields (True/False, Yes/No) are nominal qualitative data.
4. Confusing the storage type with the data type. A column of years stored as integers (2024, 2025) may be qualitative if you are grouping records by year, or quantitative if you are computing age from birth year.

Practical Exercise (5 minutes)

Here is a row from a food delivery dataset:

Classify each column. The answers are below — try it yourself first.

Answers:

• order_id — qualitative nominal (it is a label, not a count)
• customer_name — qualitative nominal
• city — qualitative nominal
• items — quantitative discrete (you cannot order 2.5 items)
• total — quantitative continuous
• rating — qualitative ordinal (1 to 5 stars)
• delivery_min — quantitative continuous

Mini Challenge

Open any spreadsheet you have — even a personal budget. List each column and classify it. If you find a column you are unsure about, that uncertainty is itself useful: it usually means the data was stored in a way that hides its true type (numbers used as labels, or text used as numbers).

Key Takeaways