iSixSigma

Is “Statistical Significance” Outdated?

Six Sigma – iSixSigma › Forums › General Forums › General › Is “Statistical Significance” Outdated?

Viewing 5 posts - 1 through 5 (of 5 total)
  • Author
    Posts
  • October 13, 2020 at 10:54 am #250439

    Fausto Galetto
    Participant

    In some papers downloaded in October 2020 I found the following:

    1. 1.    We conclude, based on our review of the articles in this special issue and the broader literature, that it is time to stop using the term “statistically significant” entirely.
    2. 2.    Nor should variants such as “significantly different,” “p < 0.05,” and “nonsignificant” survive, whether expressed in words, by asterisks in a table, or in some other way.
    3. 3.    Regardless of whether it was ever useful, a declaration of “statistical significance” has today become meaningless.

    The special issue was by The American Statistician.

    I do not agree with these statements.

    Do some of the colleagues can make some comments?

    Thanks

    0
    October 17, 2020 at 12:57 pm #250499

    Chris Seider
    ★ 10 Years ★
    Participant

    No.

    Howerver, I’d suggest you consider attaching a pdf or link or web address for link.  Hard to see what you are generating buzz about.

    1
    December 7, 2020 at 7:11 am #251244

    David007
    Participant

    I’m familiar with the paper and, for the first time, agree with you Fausto.  There are real concerns about the misuse of p-values, but that doesn’t mean we should stop using them.

    0
    January 4, 2021 at 7:39 am #251640

    tgause
    Participant

    @cseider: Hi, Chris! Try this: https://www.tandfonline.com/doi/full/10.1080/00031305.2019.1583913

    0
    January 5, 2021 at 8:55 pm #251663

    Chris Seider
    ★ 10 Years ★
    Participant

    Thanks @chebetz

    Interesting article.  It’s kind of “wonky” but they seem to be making a mountain out of a mole hill if I have the expression correctly.  Basically, just because one picks the “correct” side of the stat test with the appropriate p-value, there is uncertainty which is why things should always be proven “in the field” or else one wouldn’t get past the Improve/Control phases!

     

    0
  • Author
    Posts
Viewing 5 posts - 1 through 5 (of 5 total)

You must be logged in to reply to this topic.