Date:         Fri, 4 Sep 2009 19:57:18 -0400
Reply-To:     Arthur Tabachneck <art297@NETSCAPE.NET>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Arthur Tabachneck <art297@NETSCAPE.NET>
Subject:      Re: Geometric mean of observatons by category
Comments: To: "Kirby, Ted" <ted.kirby@LEWIN.COM>

Ted,

Take a look at:
http://groups.google.com/group/comp.soft-
sys.sas/browse_thread/thread/3ab84c59f4972e54

or, in shortened form: http://xrl.us/bfiqfa

HTH,
Art
---------
On Fri, 4 Sep 2009 19:21:08 -0400, Kirby, Ted <ted.kirby@LEWIN.COM> wrote:

>I would like to get the geometric mean of values by category.  What
>would be ideal would be if PROC MEANS had a Geometric Mean option
>analogous the MEAN SUM or other statistical calculation.  However, I
>could find no indication of this capability of PROC MEANS in the
>documentation.
>
>I can calculate the geometric mean by sorting the dataset and then
>process the data in a SAS data step using the "FIRST.var" and "LAST.var"
>operations.  However, I was wondering if it was possible to get it using
>the GEOMEAN function.
>
>For example:
>
>data have
>input category number;
>datalines;
>100 2
>110 3
>120 4
>110 8
>100 9
>100 1
>120 6
>120 3
>100 5
>110 9
>120 3
>;
>run;
>
>For this dataset I would an output that looks like this.
>
>Category        Geometric Mean of Number
>100                     2.08
>110                     6.00
>120                     2.83
>
>I feel like I am missing some really obvious or simple methodology, but
>I just can't think of anything at the moment.
>
>My real data set has 13 million observations and 500+ categories.  Thus,
>I would like the code to be as efficient as possible (i.e., not take
>hours to run, if possible).
>
>I have SAS 9.1.3 on Windows XP professional.
>
>Thanks.
>************* IMPORTANT - PLEASE READ ********************
>
>This e-mail, including attachments, may include confidential and/or
proprietary information, and may be used only by the person or entity to
which it is addressed. If the reader of this e-mail is not the intended
recipient or his or her authorized agent, the reader is hereby notified that
any dissemination, distribution or copying of this e-mail is prohibited. If
you have received this e-mail in error, please notify the sender by replying
to this message and delete this e-mail immediately.
>