Estimation of Population Attributable Fraction (PAF) for disease occurrence and application of the method for the analysis of relative importance of risk factors of type 2 diabetes

Abstract:

The Population Attributable Fraction (PAF) is a useful measure for describing the expected change in an outcome if its risk factors are modified. Estimation of PAF for both mortality and morbidity in cohort studies with censored survival data has developed in recent years. So far, however, censoring due to death in the estimation of PAF for morbidity has been ignored, resulting in estimation of a quantity which is not relevant in practice where some people are likely to die during the follow-up. In this work, the statistical methodology for the estimation of PAF for disease incidence taking censoring due to death into account is demonstrated. An application of PAF to evaluate the relative importance of risk factors of type 2 diabetes in a meta-analysis of two representative Finnish cohorts is carried out, using a new SAS program implementing the new methods.