%0 Journal Article %J Communications in Statistics-Simulation and Computation %D 2015 %T Time to diagnosis: accounting for differential follow-up times in cohort studies. %A Bůzková, Petra %E Lumley, Thomas %K 62N01 %K Covariate-dependent follow-up %K Discrete survival data %K Multi-cohort studies %K Primary 62N02 %K Secondary 62H12 %X Cox regression is widely used to analyze discrete survival time data. Differential endpoint follow-up across sub-cohorts where distribution of a covariate varies may cause typical estimators to be biased or inefficient. We demonstrate that with Cardiovascular Health Study data for incident type 2 diabetes. Two cohorts with extremely different race distribution have differential follow-up for fasting glucose levels. We study various scenarios of Cox regression. We suggest an alternative approach, Poisson generalized estimating equations with an offset to accommodate the differential follow-up. We use simulations to contrast the methods. %B Communications in Statistics-Simulation and Computation %V 44 %8 2015 %G eng %N 1 %& 247