In article <[EMAIL PROTECTED]>, Jerry Dallal <[EMAIL PROTECTED]> wrote: >Koen Vermeer wrote:
>> Hi, >> I want to test whether a set is drawn from a normal distribution. With a >> Kolmogorov-Smirnov test, I can do this for known mean and variance. The >> Lilliefors test is essentially the same, but for unknown mean and variance >> (thus estimated from the data). >> Now, in my case, I have a known mean (zero) and unknown variance, meaning >> that my situation is somewhere in between Kolmogorov-Smirnov and >> Lilliefors. Is there a separate test for this? >This is a long thread. I haven't seen this particular comment in >all of the pieces I've scanned, but if someone else has made it, I'm >sorry for the duplication. >Often, K-S like tests are of limited value because they are most >sensitive to departures from normality in the center of the >distribution. When normality is an issue, it usually involves >behavior in the tails, which is where KS-like tests are least >sensitive. The KS test detects Pitman alternatives roughly equally throughout the range. If one wants to test for small deviations near the tails, a specialized test should be used, and it still is not easy. The AD test emphasizes the tails more, but because it integrates the weighted deviations, this does not do as good a job if the non-normality is essentially only in the tails. -- This address is for information only. I do not claim that these views are those of the Statistics Department or of Purdue University. Herman Rubin, Deptartment of Statistics, Purdue University [EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
