iSixSigma

Normal Probability Plot Question

Six Sigma – iSixSigma Forums Old Forums General Normal Probability Plot Question

Viewing 5 posts - 1 through 5 (of 5 total)
  • Author
    Posts
  • #41371

    geekus
    Participant

    I ran a normal prob plot on some data today.  It’s continuous data and it is several weeks worth of data points.
    I have a p-value of 0.032 which i believe indicates that the data is normal.
    I am new however and I hate seeing an output with values on it that i dont understand.  What does the A-squared value of 0.757 represent?  The thing is, its directly above the p-value and if i show somebody this chart and they ask me what a-squared means..and i dont have a good explanation then the credibilty of the entire plot could be in question.
    Also, I dont understand what the probablilty scale is telling me.  The line is running up and to the right.  I know that the dots are N and that they tell a story but what is the line telling me?
    I’m very new at this and i just want to really understand what the tools are telling me.
    thanks
    geekus

    0
    #129580

    geekus
    Participant

    Anderson-Darling…..forgot to mention.

    0
    #129583

    CT
    Participant

    P-value = 0.05
    A-squared is the test statistic for the Anderson-Darling Normality test. It is a measure of how closely a dataset follows the normal distribution. The null hypothesis for this test is that the data is normal. So if you get an A-squared that is fairly large, then you will get a small p-value and thus reject the null hypothesis. Small A-squared values imply large p-values, thus you cannot reject the null hypothesis.
    There is a ton of information on this site, and little investigation will go a long ways, just enter a keyword search and do some reading . The answers your looking for are here
    CT

    0
    #129584

    jimmie65
    Participant

    Try the help menu in Minitab. Open the dialog box for probabilty plot and clock the Help button, then search through that entry. You’ll probably find some interpretation information under Example.
    If it’s not there, type your term in the search box.

    0
    #129585

    mZ
    Participant

    CT:
    normal = P-value >= 0.05? Is this right?
    If the test is against a theoretical Normal distribution, as the p-value getting larger, it means your data is getting closer to a normal distribution. When the A-sq is close to 1, then you can say your data is distriuted normally.
    My two cents.
    mz

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

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