lip: Scottish Lip Cancer Data

In mdhglm: Multivariate Double Hierarchical Generalized Linear Models

Description

Clayton and Kaldor (1987) analyzed observed and expected numbers of lip cancer cases in the 56 administrative areas of Scotland with a view to produce a map that would display regional variations in cancer incidence and yet avoid the presentation of unstable rates for the smaller areas. The expected numbers had been calculated allowing for the different age distributions in the areas by using a fixed-effects multiplicative model; these were regarded for the purpose of analysis as (Intercept)s based on an external set of standard rates. Presumably the spatial aggregation is due in large part to the effects of environmental risk factors. Data were available on the percentage of the work force in each area employed in agriculture, fishing, or forestry. This covariate exhibits spatial aggregation paralleling that for lip cancer itself. Because all three occupations involve outdoor work, exposure to sunlight, the principal known risk factor for lip cancer, might be the explanation.

Usage

data("lip")

Format

A data frame with 56 observations on the following 4 variables.

y

observed number of lip cancer

n

expected number of lip cancer

x

percentage of the work force in each area employed in agriculture, fishing, or forestry

county

county number for 56 areas

References

Clayton, D.G. and Kaldor, J. (1987). Empirical bayes estimates of agestandardized relative risks for use in disease mapping. Biometrics, 43, 671–681.

mdhglm documentation built on May 2, 2019, 5:52 a.m.