We used disease mapping for health impact assessment of the national airpor
t of the Netherlands. Spatiotemporal models were used to relate hospital di
scharge data for acute myocardial infarction and bronchitis in 1991, 1992 a
nd 1993 to noise and distance from the airport. To compare models a discrep
ancy measure (expected predictive deviance) proposed by Carlin and Louis wa
s used. The best fitting model was the most general one with inclusion of s
patial and temporal components. Results on the effects of the covariates no
ise and distance from the airport were somewhat inconsistent between men an
d women and between the two diseases: for women no association between bron
chitis and distance from the airport was found, whereas for men no associat
ion between acute myocardial infarction and noise was found. Copyright (C)
2000 John Wiley & Sons, Ltd.