On Wed, 22 Oct 2003, Luca Meyer wrote: > I'm running parallel chi-squared tests on the same sample, and I > have sort of noticed that if I select a somehow smaller set of > observations I tend to get smaller, less significative Chi-Squared > values. > > Is this the case? I mean, chi-squared values are sort of dependent > upon sample sizes?
Yes. All statistical tests are more sensitive to departures from whatever the null hypothesis specifies when sample sizes are large, than they are when sample sizes are small. (E.g., the standard error of a sample mean diminishes in proportion to the square root of the sample size: so for larger samples the "standard score" (z or t) associated with an hypothesis test tends to be larger.) > If so, what woudl be a correction/alternative test that avoids this > dependency? There ain't no such animal. "This dependency" comes with the territory, and cannot be avoided. Good luck anyway! -- DFB. ----------------------------------------------------------------------- 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/ . =================================================================
