Maps of morbidity or mortality rates, whether considered individually
or as a layer in a geographic information system application, invite m
ultiple comparisons of area rates. However, comparisons of rates acros
s different populations require standardization of the age-specific ra
tes to account for differences in population age structures. The indir
ect standardization method, or equivalently the standardized mortality
ratio (SMR), has been recommended for small areas where age-specific
rates can be quite variable. Although theoretically equivalent to dire
ctly adjusted rates under the assumption of independent age and area e
ffects, indirect summary measures are not comparable across areas when
this assumption is violated. We tested the validity of this assumptio
n for the 10 most common causes of death in the United States during 1
980-84 and examined the geographic clustering apparent when categorize
d death rates, adjusted by different methods, are presented as themati
c maps. Although overall agreement between the methods was good (rank
correlation coefficient > 82 per cent for each cause), when the adjust
ed rates were classified into quintiles 18 per cent of the states fell
into different categories depending on the method of adjustment. Usin
g an internal standard for the indirect method reduced this discrepanc
y to 4.9 per cent. However, both traditional chi-square tests and a ge
neralized logistic spline model identified significant interactions be
tween age and area for each cause of death, a violation of the assumpt
ion required for equivalence of the methods. Potential variation in ge
ographic inferences is illustrated by maps of direct and indirect rate
s and an empirical Bayes posterior mean, which is a function of these
traditionally adjusted rates. Based on these results, we recommend the
direct age-adjustment method for rate maps.