Re: Multiple comparison correction using p values alone

Bill H wrote:
Jerry Dallal wrote:

"Suppose we are given ONE p-values, say from ONE study. Study 1 tests
the hypothesis that some quantity say "Chemical X" is different than
zero in the population and using a t-test on their sample data finds
that the hypothesis may be rejected at p=0.02. May we conclude that the
probability of zero Chemical X in the popuation = (.02)?"

No! This is a classic misinterpretation of a P value.

That's exactly my point. It seemed that was what Zander was doing and
I'm not sure whether your . . . definition . . . helped.


Who knows? The problem with poorly stated questions is that they are open to interpretation about what the OP *might* have meant. One problem with the question is the one addressed here about confusion over the meaning of a P value. However, it's so common an error, one might ask whether the rest of the question made sense if P values were described properly. Then, the assumption about independence comes into the picture, and who knows what else?

I wouldn't call it a definition, either. I think what you're trying to say is that you wonder whether my original reply was relevant. That's the trouble with ill-formed questions. There's no way of knowing for sure. If what was in the OPs mind hinged on P(AB)=P(A)P(B) in general, it was; if not, then I agree that it wasn't.
.

Relevant Pages

  • Re: Multiple comparison correction using p values alone
    ... zero in the population and using a t-test on their sample data finds ... It seemed that was what Zander was doing and ...
    (sci.stat.consult)
  • Re: Multiple comparison correction using p values alone
    ... Study 1 tests the hypothesis that some quantity say "Chemical X" is different than zero in the population and using a t-test on their sample data finds that the hypothesis may be rejected at p=0.02. ... May we conclude that the probability of zero Chemical X in the popuation =?" ...
    (sci.stat.consult)
  • Re: On paired samples spontaneously arising in computer-simulated experiments
    ... wandered how nobody discovered this criterion before them). ... significantly different from zero, while both samples come from the ... so the last term drops out in the Student's t-test. ... the covariance term is subtracted. ...
    (sci.stat.math)
  • Re: Not of Interest? But how?
    ... > |> value c was carried across frames then the zero reference was also. ... > That is what you postings seemed to suggest is your view Bill ... You are the one living in a fantasy world. ... > | traveling at velocity v. relative to another frame a stationary particle ...
    (sci.physics.relativity)
  • Re: Examples of SQL anomalies?
    ... AT&T didn't send a bill, then the answer is clearly zero. ... accountant when you haven't yet received the bill. ... The computer has no business trying to second guess the question, which is why I said your example is a red herring. ...
    (comp.databases.theory)