iSixSigma

Rules of Thumb for Sample Size

Six Sigma – iSixSigma Forums Old Forums General Rules of Thumb for Sample Size

Viewing 5 posts - 1 through 5 (of 5 total)
  • Author
    Posts
  • #46206

    DD
    Participant

    I’m still more than a little in the dark regarding how to determine a valid sample size, anybody know some good references or can quote some reliable ‘Rules Of Thumb’ for this?
    I read on one post that there is a 10% margin of error between a sample size of 30 and one of 500, this is the sort of thing Id like to know; I understand about power for detecting change of sigma in t-tests for example, but what about when you don’t know much about the process at all and want a sample size that’s going to be big enough to be valid, without being too costly or time consuming?

    0
    #152368

    Rules of Thumb
    Member

    The following book might help you out:
    Gerald van Belle (2002). Statistical Rules of Thum. Wiley Series in Probability and Statistics.

    0
    #152369

    Helper
    Participant

    Hello DD,
    Send me a quick email and I will send you good rules of thumb for calculating sample sizes based on NIST standards.  It is about 2 pages with a couple of examples.  You can program the calcualtion into Excel with ease. 
    [email protected]
    Helper

    0
    #152370

    Heebeegeebee BB
    Participant

    Here is a link to the NIST/SEMATECH Engineering Statistics Handbook
    Definitely a life-saver!
     

    0
    #152371

    Heebeegeebee BB
    Participant

    Sorry,
    Here’s the link:
    http://www.itl.nist.gov/div898/handbook/

    0
Viewing 5 posts - 1 through 5 (of 5 total)

The forum ‘General’ is closed to new topics and replies.