TY - JOUR
T1 - Exploring spatial patterns of mortality
T2 - The new Atlas of United States Mortality
AU - Pickle, Linda W.
AU - Mungiole, Michael
AU - Jones, Gretchen K.
AU - White, Andrew A.
PY - 1999/12/15
Y1 - 1999/12/15
N2 - The National Center for Health Statistics, CDC, has produced an Atlas of United States Mortality which includes maps of rates for the leading causes of death in the United States for the period 1988-1992. As part of this project, many aspects of statistical mapping have been re-examined to maximize the atlas's effectiveness in conveying accurate mortality patterns to epidemiologists and public health practitioners. Because recent cognitive research demonstrated that no one map style is optimal for answering many different map questions, maps and graphs of several different mortality statistics are included for each cause of death. New mixed effects models were developed to provide predicted rates and improved variance estimates. Results from these models were smoothed using a weighted head-banging algorithm to produce maps of general spatial trends free of background noise. Maps of White female lung cancer rates from the new atlas are presented here to illustrate how this innovative combination of maps and graphs permits greater exploration of the underlying mortality data than is possible from previous single-map atlas designs.
AB - The National Center for Health Statistics, CDC, has produced an Atlas of United States Mortality which includes maps of rates for the leading causes of death in the United States for the period 1988-1992. As part of this project, many aspects of statistical mapping have been re-examined to maximize the atlas's effectiveness in conveying accurate mortality patterns to epidemiologists and public health practitioners. Because recent cognitive research demonstrated that no one map style is optimal for answering many different map questions, maps and graphs of several different mortality statistics are included for each cause of death. New mixed effects models were developed to provide predicted rates and improved variance estimates. Results from these models were smoothed using a weighted head-banging algorithm to produce maps of general spatial trends free of background noise. Maps of White female lung cancer rates from the new atlas are presented here to illustrate how this innovative combination of maps and graphs permits greater exploration of the underlying mortality data than is possible from previous single-map atlas designs.
UR - http://www.scopus.com/inward/record.url?scp=0033573303&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033573303&partnerID=8YFLogxK
U2 - 10.1002/(SICI)1097-0258(19991215)18:23<3211::AID-SIM311>3.0.CO;2-Q
DO - 10.1002/(SICI)1097-0258(19991215)18:23<3211::AID-SIM311>3.0.CO;2-Q
M3 - Article
C2 - 10602146
AN - SCOPUS:0033573303
SN - 0277-6715
VL - 18
SP - 3211
EP - 3220
JO - Statistics in Medicine
JF - Statistics in Medicine
IS - 23
ER -