Statistical significance and clinical significance

Statistical significance:

  • Statistical significance is the likelihood that results obtained were not due to chance.
  • Tests of significance estimate the probability that the results are reproduceable.
  • Data which does not reach statistical significance are too weak to reach any conclusion.
  • Just because a result achieves a p-value of 0.05, that does not make it important.
  • Statistical significance says nothing about effect size - miniscule effects can creep in under a p-value of 0.05.

Clinical significance:

  • Clinical significance is the practical importance of a treatment effect.
  • Clinical significance implies that the difference between treatments in effectiveness is clinically important, and it is possible that clinical practice will change if such a difference is seen.
  • Statistical significance is used to to inform clinical significance.