In article <[EMAIL PROTECTED]>, George Washington <[EMAIL PROTECTED]> wrote: >The standard deviation for the sampling distribution of the mean >(standard error) is given by SD/sq of n, so if the variance = 100, the >SD is (the square root of that) 10. 10/2 (the square-root of 4) gives >the standard error of 5, as you've done. I agree that's right.
>The mean of the sampling distribution equals mu, the population mean >(in this case, 100), by the Central Limit Theorum. That is, if I >sample repeatedly from any population and compute means for each of my >same-sized samples, the average of those averages will be the >population mean, provided I have enough samples. The Central Limit Theorem is not involved in the first paragraph. However, it is NOT true that the average will be the sample mean, but will be close with larger and larger probability as the amount of sampling increases. Also, the mean of the sampling distribution of the mean is the true mean if that exists, whether or not there is a finite variance. -- 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, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399 [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/ . =================================================================
