In article <[EMAIL PROTECTED]>, Donald Burrill <[EMAIL PROTECTED]> wrote: >Since a proportion is formally a mean (of a binary variable whose >possible values are 0 and 1), and the usual two-sample test for >proportions is formally identical to the two-sample test for means, >I should think that if the latter is based on a LRT, so should be the >former. > There may be some complication induced by the use of a large-sample >normal approximation, for which the LRT argument above would hold, >versus the binomial distribution procedure, for which I am less certain.
Not quite. There is a difference, especially for small and moderate sample sizes. Also, the means and variances are related, so that a t-test is not the right thing to do. -- 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/ . =================================================================
