We use cookies to enhance your experience on our website. By continuing to use our website, you are agreeing to our use of cookies. You can change your cookie settings at any time. Find out more
Oxford University Press - Online Resource Centres

Grafen & Hails: Modern Statistics for the Life Sciences

26.02.04 Eric Stolen, Dynamac Corp., Kennedy Space Center, USA

26.02.04 Eric Stolen, Dynamac Corp., Kennedy Space Center, USA
Chapter 07, page 120

Q: I'm wondering if the error referred to in the first paragraph on page 120 should be Type II rather than Type I. My reasoning is, if there is an interaction but we fail to reject (H0: no interaction) I believe that is a Type II error.

A: Eric is completely correct, and we are very grateful to him for pointing this out. The book says 'Type I' and it should say 'Type II' on both occasions on page 120. We can only apologise and promise to amend it in future printings as soon as we have the opportunity. The great statistician RA Fisher was strongly opposed to the terminology of Type I and Type II errors, which he viewed as illogical and American. It is therefore perhaps fitting that we should be corrected in their use by a reader in America!