Statistically adjusted estimates of geographic mortality profiles

The spatial variation of site-specific cancer mortality rates at the county or state economic area level can provide a) insights into possible etiologic factors and b) the basis for more detailed epidemiologic studies. One difficulty with such studies, especially for rare cancer types, is that unsta...

Full description

Saved in:
Bibliographic Details
Published in:JNCI : Journal of the National Cancer Institute 1987-05, Vol.78 (5), p.805-815
Main Authors: MANTON, K. G, STALLARD, E, WOODBURY, M. A, RIGGAN, W. B, CREASON, J. P, MASON, T. J
Format: Article
Language:English
Subjects:
Age Factors
Bayes Theorem
Biological and medical sciences
Epidemiology
Humans
Lung Neoplasms - mortality
Male
Medical sciences
Models, Biological
Probability
Regression Analysis
Time Factors
Tumors
Urinary Bladder Neoplasms - mortality
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The spatial variation of site-specific cancer mortality rates at the county or state economic area level can provide a) insights into possible etiologic factors and b) the basis for more detailed epidemiologic studies. One difficulty with such studies, especially for rare cancer types, is that unstable local area rate estimates, resulting from small population sizes, can obscure the underlying spatial pattern of disease risk. This paper presents a methodology for producing more stable rate estimates by statistically weighting the local area rate estimate toward the experience at the national level. The methodology is illustrated by the analysis of the spatial variation of two cancer types, bladder and lung, for U.S. white males over the three decades 1950-79.
ISSN:0027-8874
1460-2105