An interesting problem... Can't tell whether your suspicions are correct, from the information given. Perhaps you could say what you mean by "quite narrow" (and around what point estimate of P), and "enormous" (ditto); and for what sample size(s).
Since a P-value is, after all, a probability, values close to 0 (or 1, although that won't interest you) would naturally have narrower CIs than values close to 0.5. Whether these "natural" differences would look to you like "narrow" (for, e.g., P=0.005) vs. "enormous" (for, e.g., P=0.4) I cannot tell. Of course, it is also possible that your procedure is flawed in some way that produces more extreme differences that would justify your adjectives; but there is no detailed information about your procedure(s) that would permit one to diagnose any such imaginable flaws, let alone prescribe remedies. On Thu, 16 Oct 2003, Enda Kelly wrote: > Hi. I have a query regarding whether it is logical to place a > confidence interval about a P-value. The computation involved uses a > permutation method to produce a P-value for a hypothesis test. In an > effort to check the reliability of this P-value I have been > bootstrapping the raw data to produce a confidence interval about this > P-value. Curiously, for significant P-values the CI is in general > quite narrow, whereas for non-significant values, I get enormous CIs. > This leads me to the suspicion that there is something flawed about > the process. Am I correct in my suspicions? ----------------------------------------------------------------------- Donald F. Burrill [EMAIL PROTECTED] 56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
