Date: Thu, 22 Sep 2005 09:15:29 0600
ReplyTo: Adrian Musters <Adrian.Musters@nurs.utah.edu>
Sender: "SPSSX(r) Discussion" <SPSSXL@LISTSERV.UGA.EDU>
From: Adrian Musters <Adrian.Musters@nurs.utah.edu>
Subject: Standard Error
ContentType: text/plain; charset=USASCII
Hi everyone,
I did a oneway ANOVA in SPSS 13 with a Tukey HSD PostHoc test. In
the output I noticed that the Standard Error in the Multiple Comparisons
table was 17.30069 for each and every comparison. I am comparing the
amount of foraging in 4 different types of grass, each with 5
observations. My understanding is that the Standard Error is calculated
by dividing the Standard Deviation by the square root of the number of
observations  SD/sqrt(N)
Is the standard deviaiton that is used the standard deviation of the
whole group (N=20)? Mine is 37.44094 . So I'm wondering about the
calculation. 37.44094 / sqrt (5) = 16.7440974. Am I wrong about the
calculation for the SE? If not, is there anyone who is able to explain
the discrepancy of .55 in the two SEs?
Thanks in advance,
Adrian
