Comparing the part with the whole: should overlap be ignored in public health measures?

Background: In public health, health outcomes such as cancer incidence or mortality of subgroups are often compared with health outcomes of the whole population. Our objective was to explore the effect of overlap that occurs in such comparisons and to develop a correction factor to adjust the test statistics and confidence intervals to allow for the effect in situations where the full data are not available.

Method: The standard error of a difference between a statistic calculated for a subgroup and for the whole population was derived theoretically both ignoring and allowing for overlap.

New South Wales trends in mortality differentials between small rural and urban communities over a 25-year period, 1970-1994.

Objective: To identify trends in premature mortality differences between urban and small rural communities in NSW over a 25-years period.

Design: A longitudinal population-based study. ABS population and death data by local government area, sex and age for the period 1970 to 1994, were used to derive mortality measures for urban and small rural communities in NSW.

Socio-economic mortality differentials in Sydney over a quarter of a century, 1970-94.

Objective: To examine trends in socio-economic differentials in all-cause mortality in Sydney over a 25-year period (1970-94).

Methods: Five measures of single indicators (two for occupation, two for education and one for income) and a composite measure of socio-economic disadvantage based on Census data (the Australian Bureau of Statistics' Index of Relative Socio-Economic Disadvantage) were used as indicators of socio-economic status by local govemment area. The relationship between mortality and socio-economic status was examined using quintiles based on these six measures of socio-economic status.