MEPX
Chapter 1 of 13All chapters
  1. 1What analysis is for
  2. 2Types of data
  3. 3Collecting and sampling
  4. 4Cleaning data
  5. 5Describing the middle
  6. 6Describing the spread
  7. 7Choosing a chart
  8. 8Correlation
  9. 9Getting to causation
  10. 10Hypothesis testing
  11. 11Traps and paradoxes
  12. 12Tools of the trade
  13. 13Communicating results

Chapter 1 of 13

What analysis is for

A question first, then the numbers.

Start with the question

Analysis without a question produces charts nobody acts on. Write down what decision the answer will change before opening the data, and the right method usually becomes obvious.

  • Descriptive work says what happened. Inferential work generalises beyond the sample.
  • Predictive work says what is likely next, and needs the most care.

Honest limits

Every dataset was collected by someone, for some purpose, with some gaps. Knowing how it came into being tells you what it can honestly answer.