Types of Data and Data Sources

Not All Data is the Same

Before you can analyse data, you need to understand what kind of data you are working with. Different types of data require different analytical approaches, different tools, and different statistical methods.

This lesson covers the main types of data and where data comes from. Both are foundational knowledge that every data analyst needs.

Quantitative vs Qualitative Data

The most fundamental distinction is between data you can measure numerically and data that describes qualities.

Quantitative Data (Numerical)

Quantitative data is data that can be counted or measured and expressed as a number.

Examples:

• A product's price: 12,500 NGN
• A customer's age: 34 years
• Monthly website visitors: 85,000
• Average delivery time: 2.3 days

Quantitative data can be further split:

Discrete: Countable, whole numbers. You cannot have 2.7 customers -- it is always a whole number. Examples: number of orders, number of products, number of employees.

Continuous: Can take any value within a range, including decimals. Examples: height, temperature, revenue (NGN 15,432.67).

Qualitative Data (Categorical)

Qualitative data describes qualities or categories that cannot be meaningfully measured as numbers.

Examples:

• A customer's gender: Male, Female, Other
• Product category: Electronics, Clothing, Food
• Customer satisfaction: Satisfied, Neutral, Dissatisfied
• Country of origin: Nigeria, Ghana, Kenya

Qualitative data is further divided:

Nominal: Categories with no meaningful order. Country, product colour, payment method.

Ordinal: Categories with a meaningful order but unequal gaps between them. Satisfaction ratings (Low, Medium, High), education level (Primary, Secondary, University).

Structured vs Unstructured Data

Another key distinction is whether data is organised in a predictable format.

Structured Data

Structured data is organised in rows and columns -- like a spreadsheet or database table. It is easy to query with SQL and analyse with spreadsheets.

Example: A table of customer transactions:

Semi-Structured Data

Has some structure but does not fit neatly into a table. JSON (JavaScript Object Notation) and XML are common examples. APIs typically return semi-structured data.

{
  "customer": "Amara Okafor",
  "orders": [
    { "id": "ORD-001", "amount": 8500 },
    { "id": "ORD-002", "amount": 3200 }
  ]
}

Unstructured Data

No predefined structure. This is the hardest to analyse but makes up about 80% of all data in the world.

Examples:

• Customer reviews and comments
• Social media posts
• Emails
• Images, audio, and video
• PDFs and documents

Analysing unstructured data often requires techniques from Natural Language Processing (NLP) and machine learning.

Primary vs Secondary Data Sources

Primary Data

Data you collect yourself, directly from the source.

Advantages: Tailored to your exact needs, higher trust in accuracy. Disadvantages: Takes time and money to collect.

Secondary Data

Data collected by someone else that you access and use.

Advantages: Already collected, often free or cheap, covers large populations. Disadvantages: May not match your exact question, may be outdated.

Internal vs External Data

Internal data lives within your organisation:

• Sales records from your CRM (Customer Relationship Management system)
• Website traffic from Google Analytics
• Financial records from your accounting software
• Customer support tickets from Zendesk

External data comes from outside your organisation:

• Market research reports
• Social media data
• Economic indicators
• Competitor pricing (scraped from websites)

Most analytics projects use a combination of both.

Common Data Formats You Will Encounter

As a data analyst, you will spend a surprising amount of time converting between these formats and cleaning the data within them.