Abstract
We first point out that variance estimates for regression coefficients in exposure stratified case-cohort studies (Borgan et al., 2000) can easily be obtained from influence terms routinely calculated in standard software for Cox regression. We also place the estimators proposed by Chen (2001) for a general class of cohort sampling designs within the Borgan et al. framework by allowing for post-stratification on outcome. This facilitates simple variance estimation for this class of cohort sampling designs. Finally, we extend the approach of Chen to accommodate stratified designs with surrogate variables available for all cohort members, such as stratified case-cohort and counter-matching designs.