iSixSigma

Sample size…Why 30?

Six Sigma – iSixSigma Forums Old Forums General Sample size…Why 30?

Viewing 3 posts - 101 through 103 (of 103 total)
  • Author
    Posts
  • #173235

    Arlene
    Participant

    sam,
    im a beginner in stat. im a math major but taking up master in stat. i am also curious about samle size n=30. i would really appreciate if u could send me info regarding this matter.
    my email:[email protected]
    thanks a lot!
    more power and GOD bless always!

    0
    #176349

    source?
    Member

    Can you give references for the claim that symmetry/normality at n=25 has a LLN justification?Thanks!

    0
    #189263

    Karim
    Participant

    Hopefully this will be of use to other lost souls who stumble upon this rather old thread.I am a statistics teacher and I use Stats: Modeling the Real World by Bock, Velleman, and De Veaux. I recommend the book highly if you want to understand basic statistics. They address the issue of required sample size in order to perform a t-test as follows (2nd ed., pg. 534):”Nearly Normal Condition: The data come from a distribution that is unimodal and symmetric.
    “Check this condition by making a histogram or a Normal Probability Plot. The importance of Normality for Student’s-t depends on the sample size…
    “For very small samples (n < 15 or so), the data should follow a Normal model pretty closely…if you do find outliers or strong skewness, do not use these methods.
    “For moderate sample sizes (n between 15 and 40 or so), the t methods work well as long as the data are unimodal and reasonably symmetric. Make a histogram.
    “When the sample size is larger than 40 or 50, the t methods are safe to use even if the data are skewed.”They do talk about just using 30 as a rule of thumb elsewhere (I can’t put my finger on it right now), as long as the data are unimodal and reasonably symmetric.But please notice these are the MINIMUM conditions to perform a t-test. If you want to figure out the sample size you need for your situation, you have to estimate it using margin of error. In most cases, you will find you need a number much larger than 30. Here is a useful article explaining how to calculate the required sample size:http://www.osra.org/itlpj/bartlettkotrlikhiggins.pdf

    0
Viewing 3 posts - 101 through 103 (of 103 total)

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