Date:         Fri, 17 Aug 2007 13:03:57 -0700
Reply-To:     "Pardee, Roy" <pardee.r@GHC.ORG>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Pardee, Roy" <pardee.r@GHC.ORG>
Subject:      Re: Trimmed means
In-Reply-To:  A<OFB3B615CA.7290ED67-ON0325733A.006C56D4-0325733A.006D36F9@serasa.com.br>
Content-Type: text/plain; charset="us-ascii"

UNIVARIATE does support both WEIGHT and FREQ statements--do those not
serve your needs?

-----Original Message-----
From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of
Ricardo G Silva
Sent: Friday, August 17, 2007 12:53 PM
To: SAS-L@LISTSERV.UGA.EDU
Subject: Trimmed means

Dear Users,

I need to calculate trimmed means (TM) for various time series. However,
the option available in PROC UNIVARIATE does not allow the possibility
to introduce a weight for each observation of the series.
Basically, the TM in SAS  involves a sum from 1 to N of w_i, and I need
a sum from 1 to N of w_i*c_i.

This methodolgy are used to compute cores for consumer prices indexes.

Anybody already developed a code to implement it?

Thanks a lot

Rick