From peter@caliper.com Tue Jul 10 06:40:45 2001 Received: from mxu3.u.washington.edu (mxu3.u.washington.edu [140.142.33.7]) by lists.u.washington.edu (8.11.2+UW01.01/8.11.2+UW01.04) with ESMTP id f6ADei0124702 for ; Tue, 10 Jul 2001 06:40:44 -0700 Received: from iris.caliper.com (iris.caliper.com [198.22.17.3]) by mxu3.u.washington.edu (8.11.2+UW01.01/8.11.2+UW01.04) with ESMTP id f6ADehX22019 for ; Tue, 10 Jul 2001 06:40:44 -0700 Received: from HEMLOCK.caliper.com (hemlock.caliper.com [198.22.17.104]) by iris.caliper.com (8.9.3/8.9.3) with ESMTP id JAA24972; Tue, 10 Jul 2001 09:39:25 -0400 (EDT) Message-Id: <4.3.1.2.20010710092402.015ecfe0@iris.caliper.com> X-Sender: peter@iris.caliper.com X-Mailer: QUALCOMM Windows Eudora Version 4.3.1 Date: Tue, 10 Jul 2001 09:38:53 -0400 To: "Pickle, Linda (NCI)" From: "Peter H. Van Demark" Subject: Re: FW: Zip Codes, ZCTA and areal interpolation Cc: waphgis@u.washington.edu In-Reply-To: <622E01CFB200F446B3E3EE069FA85A9123A066@nihexchange7.nih.go v> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Linda: >Hi - Perhaps I, too, misunderstand ZCTAs, but even if zip codes and ZCTAs >have the same #s, they don't necessarily refer to the same space. At least >this is what the Census person presented to us. If your #3 were true, I >could use the ZCTA populations and apply them to my zip coded data. What am >I missing? Go back to #1. There is no way to accurately bound the mailing addresses in a ZIP Code, so the space bounded is moot. The important thing is the mailing addresses included in a ZIP Code. If you have a mailing address with an accurate ZIP Code, that household is in that ZIP Code. If you have a lot of clients and their accurate ZIP Codes then (at that point in time) you have accurate groupings by ZIP Code. The trick is with other data reported by ZIP Code: is it the same group of households? Probably not. It has to do with: 1. The date of your data 2. The date of the other data 3. The way the households were grouped for each The Census Bureau is not going to report data for any smaller unit than blocks, if then, for confidentiality reasons. Therefore, ZCTAs are groups of blocks. So there will be some fuzz on the edges: households that they know are in one ZIP Code are counted in another. Maybe their method tries to balance things out, so if some households end up on the wrong side of the line, about the same number are sent back somewhere else. Unless some vendor of demographic data can do a better job than the Census Bureau of accurately counting everyone and put them in the right ZIP Code, which would be unlikely, you will have to go with ZCTAs as your denominator for ZIP Code-based analysis. Peter ---------------------------------------------------------------- Peter Van Demark Director of GIS Products and Training Phone: 617-527-4700 Caliper Corporation Fax: 617-527-5113 1172 Beacon Street E-mail: peter@caliper.com Newton MA 02461-9926 Web site: http://www.caliper.com .