Date:         Fri, 17 Jan 2003 18:04:53 -0500
Reply-To:     Art@DrKendall.org
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Arthur J. Kendall" <Art@DrKendall.org>
Organization: Social Research Consultants
Subject:      Re: Repeating Means Tables
Comments: To: "Conner, Jeremy" <Jeremy.Conner@ghv.com>
Content-Type: text/plain; charset=us-ascii; format=flowed

Is this what you need?

compute constant=1.
aggregate outfile='d:\project\temp.sav' /break =constant
  / grand = sum(var1).
match files file=* /table='d:\project\temp.sav' by constant.
compute comp1 = (grand - var1)/202.
list /vars= id var1 comp1.
execute.

Is var1 a mean for that center? If so you might want to weight each
center in computing the grand sum.

Hope this helps.

Art
Art@DrKendall.org
Social Research Consultants
University Park, MD USA


Conner, Jeremy wrote:
> I have data for 203 hospital centers and I want to compare each center with
> the mean of the other 202 centers. I have 1 row of data for each center. My
> data looks something like the following:
>
> Id      var1    id2
> 3       1.5     1
> 5       2.3     0
> 18      1.4     0
> .       .       .
> .       .       .
> .       .       .
> 203     2.5     0
>
> I know I can manually program syntax to read something as follows:
>
>
> Compute id2=0.
> Do if id=3.
> Compute id2=1.
> End if.
> Exe.
> MEANS
>         TABLES=var1 BY id2.
>         /CELLS MEAN COUNT STDDEV.
> Compute id2=0.
> Do if id=5.
> Compute id2=1.
> End if.
>
>
> Etc..... for all 203 centers.
>
> My ID numbers are not consecutive numbers, but they are unique and numeric.
> I know there has to be a way to automate this process. I appreciate any help
> from the list on this matter.
>
> Jeremy
>