Data

  • Data is information
  • But data is not knowledge


  • Data may or may not contain a pattern
  • That pattern is the knowledge


  • If it contains a pattern we might be able to exploit it…
  • Exploitation of patterns in data is called “data science”

Data

  • Remind everybody just because you exploit data doesn’t make you evil.
  • It’s an ethical question…
  • Now show photo of Jeff Bezos

Data

  • Remind everybody just because you exploit data doesn’t make you evil.

  • It’s an ethical question…

  • Now show photo of Jeff Bezos

Mathematics

  • Mathematics is the language of patterns
  • Patterns can be expressed in ways other than mathematical notation


  • But all patterns can be expressed mathematically

Mathematics

  • Mathematics is the language of patterns
  • Patterns can be expressed in ways other than mathematical notation


  • But all patterns can be expressed mathematically

What is statistics

  • Is a branch of mathematics
  • Allows us to make probable conclusions from samples
  • Does it by attempting to separate the signal (pattern) from the noise

Signal vs noise

Summary

  • Your brain will convince you to see patterns in noise
  • There are statistical ways of separating the signal (pattern) from the noise
  • If there is a pattern we can exploit it e.g. improve the effectiveness of the intervention

Next up…

Data disasters and how to avoid them