Video: Randomisation Variation [6:01]

Random assignment of experimental units to treatment groups is the most reliable way people know for constructing fair tests of treatments. But it is by no means perfect. We’ll show you how varied the differences between groups can be simply due to random labelling.

(See also the Review Questions following the movie)

[Illustrated transcript (pdf)]

After you’ve watched this video, you should be able to answer these questions:

  • What is randomisation variation and why is it a problem?
  • How can we reduce the levels of randomisation variation?