Directly standardized mortality rates are examples of weighted sums of Poisson rate parameters. If the numbers of events are large then normal approximations can be used to calculate confidence intervals, but these are inadequate if the numbers are small. We present a method for obtaining approximate confidence limits for the weighted sum of Poisson parameters as linear functions of the confidence limits for a single Poisson parameter, the unweighted sum. The location and length of the proposed interval depend on the method used to obtain confidence limits for the single parameter. Therefore several methods for obtaining confidence intervals for a single Poisson parameter are compared. For single parameters and for weighted sums of parameters, simulation suggests that the coverage of the proposed intervals is close to the nominal confidence levels. The method is illustrated using data on rates of myocardial infarction obtained as part of the WHO MONICA Project in Augsburg, Federal Republic of Germany.
In the second World Health Organization MONItoring Trends and Determinants in CArdiovascular Disease (MONICA) Augsburg survey in 1989-1990 (#1=4,940), the association between nephelometric plasma fibrinogen level and lifestyle-related potential determinants was assessed in 4,434 subjects aged 25-74 years (89.8% of participants). Irrespective of pregnancy and the use of oral contraceptives, crude fibrinogen values were consistently higher in women than in men of all ages (age-standardized difference, 12.2 mg/dl; 95% confidence interval, 7.0-17.4 mg/dl). Fibrinogen concentrations were positively correlated (psO.0001) with age, body mass index, and waist-to-hip ratio in both sexes and with cigarette smoking In men and were negatively correlated with alcohol consumption in both sexes. In multiple linear regression analyses using categorized determinants as independent variables, a strongly J-shaped relation for body mass index in women and a linear association for waist-to-hip ratio in men were revealed. Smoking had a dose-dependent effect on fibrinogen concentration in men but a lesser effect in women. For alcohol consumption a U-shaped association was found, particularly in men. The curvilinear relations were confirmed in multiple polynomial regression models using continuous determinant variables. The potential epidemiological impact of a determinant was assessed by calculating differences in adjusted fibrinogen concentrations associated with the 10th and 90th percentile values of the determinant distributions actually observed among the study participants. This impact on the population fibrinogen level was most pronounced for age in both sexes, followed by body mass index, cigarette smoking, and alcohol consumption in women and by smoking, waist-to-bip ratio, and alcohol consumption in men. About 29% of the total variance in female and 26% in male fibrinogen values were explained by the three lifestyle factors plus age. Our findings are consistent with the hypothesis that fibrinogen may be an etiologic link between certain lifestyle characteristics and the course of cardiovascular disease. {Arterio- sclerosis and Thrombosis 1992;12:780-788) KEY WORDS • fibrinogen • cardiovascular disease risk factors • body mass index • waist-to-hip ratio • cigarette smoking • alcohol consumption T he evidence that clotting factors may be important in the evolution of atherosclerotic vascular disease was initially derived from case-control 1 " 3 and angiographic 4^ studies in which men with clinically manifest coronary heart disease showed elevated mean fibrinogen levels. Further evidence came from a number of prospective epidemiological studies indicating that plasma fibrinogen levels were strongly predictive of coronary heart disease and stroke incidence and mortality. 6 -12 An as-yet-undetermined part of the association between traditional risk factors and cardiovascular disease From the GSF-Institute of Epidemiology
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.