From picklel@mail.nih.gov Mon Jul 24 08:14:18 2000 Received: from mxu2.u.washington.edu (mxu2.u.washington.edu [140.142.32.9]) by lists.u.washington.edu (8.9.3+UW00.05/8.9.3+UW99.09) with ESMTP id IAA138900 for ; Mon, 24 Jul 2000 08:14:17 -0700 Received: from ims.hub.nih.gov (ims.hub.nih.gov [128.231.90.111]) by mxu2.u.washington.edu (8.9.3+UW00.02/8.9.3+UW99.09) with ESMTP id IAA03504 for ; Mon, 24 Jul 2000 08:14:16 -0700 Received: by ims.hub.nih.gov with Internet Mail Service (5.5.2651.58) id <38RHYRQ0>; Mon, 24 Jul 2000 11:14:03 -0400 Message-ID: <2733FFCBA624D4119DAA0008C75D7725586AFD@nihexchange7.nih.gov> From: "Pickle, Linda (NCI)" To: "'waphgis@u.washington.edu'" Subject: RE: health data mapping Date: Mon, 24 Jul 2000 11:14:00 -0400 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2651.58) Content-Type: text/plain; charset="iso-8859-1" Jenks refers to a method of assigning categories "optimally", so that the error sums of squares is less within the category than between categories. Can a geographer/cartographer add to this? Linda Williams Pickle, Ph.D. Senior Mathematical Statistician Statistical Research and Applications Branch Surveillance Research Program Division of Cancer Control and Population Sciences National Cancer Institute EPN Room 4103, MSC 7359 6130 Executive Blvd., Bethesda, MD 20892 (for overnight delivery, use Rockville, MD 20852) Branch phone: 301-435-7739; Fax: 301-435-3710 Email: picklel@mail.nih.gov -----Original Message----- From: Dick Hoskins [mailto:rhoskins@home.com] Sent: Monday, July 24, 2000 10:10 AM To: waphgis@u.washington.edu Subject: Re: health data mapping Linda: What are Jenks? Everyone else: I saw a web site (a geography dept?) that had some materials , maybe a tutorial, on categories and maps, but I cannot find it again. Any ideas where that may be? Dick Hoskins rhoskins@home.com ----- Original Message ----- From: "Pickle, Linda (NCI)" To: Sent: Monday, July 24, 2000 5:52 AM Subject: RE: health data mapping > I have been working with Cindy Brewer of Penn State to compare methods of > creating categories for health rate maps. Quantiles seem to convey the > underlying data accurately for all types of questions and even non-normal > data distributions. Other methods tested included Jenks and equal width > intervals (+ 4 others) > > Linda Williams Pickle, Ph.D. > Senior Mathematical Statistician > Statistical Research and Applications Branch > Surveillance Research Program > Division of Cancer Control and Population Sciences > National Cancer Institute > EPN Room 4103, MSC 7359 > 6130 Executive Blvd. > Bethesda, MD 20892 > (for overnight delivery, use Rockville, MD 20852) > Branch phone: 301-435-7739 > Email: picklel@mail.nih.gov > > > -----Original Message----- > From: Rosmaire Kelly [mailto:rosmaire@worldnet.att.net] > Sent: Friday, July 21, 2000 8:41 PM > To: waphgis@u.washington.edu > Subject: health data mapping > > Are there conventions for creating categories when mapping > health > data? I am involved in a project to map a variety of health > data in > Ohio at county (and possibly census tract) level, and would > appreciate any information from anyone who has been involved > in this > sort of work. > > Thanks in advance, > > Rosmarie Kelly > MPH student .