Results from the univariate analysis of prostate cancer mortality and incidence do not take into account the effect of different covariables, which might influence the SMR and SIR. Various covariables where considered to model longitudinal effects: age, calendar year, year of immigration, length of stay in Germany; cohort was considered for the analysis of mortality. Multivariate Poisson regression did not show any significant effect of the considered covariables on mortality (data not shown).
