Quantitative and Qualitative Variables: A Guide for SMEs

The difference between quantitative and qualitative variables can be understood in 30 seconds:

• Quantitative: answers how much? with a number (ticket, visits, points).

• Qualitative: answers what type? with a category (favorite drink, branch, channel).

This separation decides whether you send the same promotion to your entire base or trigger an action that actually drives revenue.

Quick coffee shop example (above the fold)

Imagine a coffee shop in Puebla with a loyalty CRM. In one week you see:

The same “average sale” does not mean the same customer. Qualitative and quantitative variables together tell you who to target, with what offer, and when.

What quantitative variables are

Quantitative variables measure quantities. In a brick-and-mortar business, they are data that you can add up, average, or compare month after month without making up meanings.

In coffee shops, restaurants, and businesses with loyalty programs, they usually look like this:

• Ticket / purchase amount (MXN)

• Frequency (visits per week or month)

• Days since last purchase

• Accumulated or redeemed points

• Units per ticket (drinks, dishes, add-ons)

• Revenue per customer in a period

How to use them in operations

1. Detect real value: a customer spending $180 every 15 days is not “the same” as one spending $50 three times a week.

2. Set goals per branch: average ticket and visits, not just total revenue.

3. Prioritize reactivation: if “days since last purchase” passes your threshold (for example, 14 days in an office coffee shop), the message goes out before the habit cools down.

4. Measure campaigns: not just open rates; look at the ticket and repurchase rate of the targeted segment.

Practical rule: if the data allows for “double” or “half” with commercial meaning (visits, dollars, points), it is almost certainly quantitative.

Mini worksheet (CRM fields)

Copy these fields into your CRM or a simple sheet:

With Swirvle, those fields stop living in disconnected Excel files: each purchase updates history, points, and frequency to segment without guessing.

What a qualitative variable is

A qualitative variable classifies. It doesn't say how much they spent; it says what they prefer, where they buy, or how they want to be contacted.

Typical examples in food SMEs and physical retail:

• Preferred drink or dish

• Usual branch

• Channel (counter, WhatsApp, delivery)

• Payment method

• Preferred reward type (points, coupon, free product)

• Loyalty level on a scale (new / frequent / loyal) — qualitative ordinal

Why it matters as much as the number

Knowing that the average ticket went up is useful. Knowing that it went up in cold drinks + pastries at the Downtown branch via WhatsApp is actionable: inventory, sales pitch, and campaign channel.

A business doesn't need advanced statistics. It needs to avoid mixing categories with absurd averages (“branch average”) and instead cross category + number.

Quantitative and qualitative variables together (what actually sells)

The commercial magic lies in crossing them:

This logic powers data-driven decision making and relies on sales reports with examples to keep you from relying on pure intuition.

Mistakes that cost margin

1. Averaging categories. “Average payment method” is useless. Use counts or % share.

2. Treating IDs as metrics. Receipt numbers or customer IDs identify; they do not measure behavior.

3. Same promo for everyone. Without qualitative variables, you give away margin to someone who was already going to buy.

4. Inventing order where there is none. Branch A is not “greater” than branch B; they are different categories.

5. Looking only at the consolidated numbers. The total figure hides the branch that has already lost frequency.

Simple scales (without getting complicated)

You don't need to memorize statistics. Just three operational distinctions:

1. Nominal (qualitative): categories without order — branch, flavor, channel.

2. Ordinal (qualitative): categories with order — new → frequent → loyal.

3. Ratio (quantitative): numbers with a true zero — visits, money, points.

This avoids misleading charts (lines for “payment types”) and made-up averages.

5-second cues

• “Came 6 times” → quantitative

• “Prefers cold drinks” → qualitative

• “Ticket above average” → quantitative

• “Buys at Downtown” → qualitative

• “High loyalty” → ordinal qualitative

Example of a segment ready for WhatsApp

Segment name: At-risk high-ticket cold drinkers
Rules:

• favorite_category = Cold (qualitative)

• average_ticket_30d ≥ 120 (quantitative)

• days_since_last_purchase ≥ 14 (quantitative)

• branch = Downtown (qualitative)

Message (example): “Your cold brew misses you. This week: +20 points if you return to Downtown before Friday.”
What you measure: redemption, ticket of the return visit, second visit within 7 days.

This is customer segmentation applied to the sales counter, not to an academic paper.

3-step plan for this week

1. Audit 10 fields of your database: mark them as Qn (quantitative) or Ql (qualitative).

2. Build a mixed segment (e.g., ticket > $120 + cold category + visits ≤ 2 in 30 days).

3. Launch an action and measure only that segment: 7/14-day repurchase rate, ticket, and points redemption.

If you want to move from isolated data to segments and loyalty campaigns that actually drive repeat visits in your coffee shop or restaurant, Swirvle centralizes customers, purchasing habits, points, and results by branch to act with context — rather than end-of-day guesswork.