Justification for beta error (power of the test)
September 21, 2006 at 2:29 pm #44663
Does anybody know of a reference that recommends and 80% power (0.20 beta risk) as a minimum/rule of thumb for power and sample size calculations? I’m aware that setting up your beta risk is really up to you and the criticality of the process, but if you need a place to start, I know in all my statistics and SS classes, a minimum power of 80% is typically used.
As for confidence (alpha risk), typically the minimum is 90%.
Thanks0September 30, 2006 at 6:47 pm #144081
k.bhadrayyaParticipant@k.bhadrayya Include @k.bhadrayya in your post and this person will
be notified via email.
Please see the following reference book for the power and sample sizealculatiopns.
The title of the Book.Design of Experiments With Mninitab written by Paulmathews Chpter No.11, pagesnos. 466 onwards for samplesize calculations along with the power.It is Published by :Quality Press,600 N.Plankinton Avenue,Milwaukee, Wisconsin 53203Call toll free 800-248-1946Fax 414-277-1734WWW.asq.orghttp://qualitypress.asq.orgEmail:[email protected] Library Book No:QA 277,M377,2005 i9n californiaUCI libray. Perihaps the number may hav esimilarnotation in all Libraries.This book details with an exapmnle how to calculatefor RSM etc along with power and graphs.Hope this shpould help you.
If it satisfy your requirement, let me know. My mail ID:[email protected]0
The forum ‘General’ is closed to new topics and replies.