Update: We are now collecting Disclosures from all users who edit content. You will be prompted to update these when you next edit content or you can complete your disclosures at any time in your user profile. This has been reflected in an updated terms-of-use.

Type II error

Last revised by Dr Henry Knipe on 06 Apr 2015

Type II errors (beta errors, β) occur when we accept that there is no difference between two experimental groups, when in fact, there is a difference.

The p-value does not give a direct indication of the likelihood of a type II error; if the p-value is >0.05, this does not necessarily mean that the two experimental groups are similar. This would only be true if the study is powered to a size to detect a difference if it were present 2.

By convention, we try to keep β = 0.15-0.20

Factors that affect the β:

  • the size of the difference between the groups
  • variability within groups
  • the likelihood of committing a type I error
  • sample size: the larger study, the more power and the less likelihood of a β error

ADVERTISEMENT: Supporters see fewer/no ads

Cases and figures

  • Figure 1: alpha and beta error
    Drag here to reorder.
  • Updating… Please wait.

     Unable to process the form. Check for errors and try again.

     Thank you for updating your details.