Type II error
Citation, DOI, disclosures and article data
At the time the article was created Matt A. Morgan had no recorded disclosures.View Matt A. Morgan's current disclosures
At the time the article was last revised Henry Knipe had no recorded disclosures.View Henry Knipe's current disclosures
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
- 1. Blackmore CC. The challenge of clinical radiology research. AJR Am J Roentgenol. 2001;176 (2): 327-31. doi:10.2214/ajr.176.2.1760327 - Pubmed citation
- 2. Altman DG. Practical Statistics for Medical Research (Chapman & Hall/CRC Texts in Statistical Science). Chapman and Hall/CRC. ISBN:0412276305. Read it at Google Books - Find it at Amazon
- 3. Trout AT, Kaufmann TJ, Kallmes DF. No significant difference . Says who?. AJNR Am J Neuroradiol. 2007;28 (2): 195-7. Pubmed citation