Randomisation

• Randomisation:

  • ensures there is no systematic bias
  • minimises the chance in a clinical trial that prognosis will be different from person to person
  • this means that if we do see different prognosis's in the outcome, we can be more confident that it was because of the independent variable/manipulation itself
• Randomisation:

  • It minimises the risk that important differences at baseline will change the results
  • In non-randomised studies you can only control for known confounders
  • Successful randomisation minimised the risk even for things you don’t know about
  • Even imbalances at baseline occur at random and are unsystematic biases