Just to further elaborate, the means that are connected by lines are not significantly different from each other. If two means do not share a line, then they are significantly different.
-----Original Message----- From: "William B. Ware" <[EMAIL PROTECTED]> To: Paula <[EMAIL PROTECTED]> Date: Mon, 17 Mar 2003 08:23:29 -0500 (EST) Subject: Re: How to explain this post hoc comparison? Paula, First, it's a Tukey HSD test, named after John Tukey, the statistician who developed the procedure. Second, the letters underneath the group labels represent "lines". Any two groups underscored by a common line are not different. That is, they constitute a "homogeneous" family. So, groups 1 & 2 are one family. Groups 2, 6, & 3 are another family. Groups 3, 5, & 6 are a third family. WBW __________________________________________________________________________ William B. Ware, Professor Educational Psychology, CB# 3500 Measurement, and Evaluation University of North Carolina PHONE (919)-962-7848 Chapel Hill, NC 27599-3500 FAX: (919)-962-1533 http://www.unc.edu/~wbware/ EMAIL: [EMAIL PROTECTED] __________________________________________________________________________ On 16 Mar 2003, Paula wrote: > HI, > I have done a Turkey's HSD test for a one-way ANOVA in SAS. > I don't know how to explain the result: > > 1 2 6 3 5 4 > aaa > bbbbb > ccccc > > thanks for your help!! > . > . > ================================================================= > Instructions for joining and leaving this list, remarks about the > problem of INAPPROPRIATE MESSAGES, and archives are available at: > . http://jse.stat.ncsu.edu/ . > ================================================================= > . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . ================================================================= . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
