Data Science · Beginner level

Beginner level · Module 1: The Data Science Process · Lesson 2 of 3

Data Types and Sources

Recognise different kinds of data and where organisations get it, with the strengths and weaknesses of each source.

In this lesson you will

  • Classify variables as numeric or categorical
  • Compare common data sources and their limits

Key concepts

numeric and categoricalordinalsurveys and administrative datamobile data collection

The lesson

Variables are numeric (age, income) or categorical (district, water source). Some categories have an order (ordinal), such as 'never, sometimes, always'. The type decides which summaries and charts make sense.

Organisations use surveys, administrative records (school registers, clinic logs), mobile data collection tools such as KoboToolbox and ODK, and sometimes sensor or phone data. Each has gaps: surveys rely on who answered, registers on who was registered.

Ask who collected the data, when, how and for what purpose. Data collected for one purpose may be misleading for another.

Step by step

  1. Classify the variables in a sample survey.
  2. Identify which are ordinal.
  3. Compare a survey and a register as sources for the same question.
  4. Write down who might be missing from each.

Practice activity

Write a data source note for the water access survey: who collected it, how and what its limits are.

Expected result: An accurate note covering collection method, coverage and likely gaps.

Check your understanding

  1. Is 'satisfaction: low, medium, high' numeric or categorical?

    Show answer

    Categorical, and ordinal because it has an order.

  2. Why ask how data was collected?

    Show answer

    Collection method decides who is represented and what the data can show.

Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.