Online Program

Weight calibration to improve the efficiency of absolute risk estimates from nested case-control designs (310032)

We study the efficiency of pure absolute risk estimates (one minus the survival function) when some covariates are only available for case-control samples nested in a cohort. Researchers have calibrated design-based inclusion probability weights to increase the efficiency of relative hazard estimates under the Cox model framework. We extend weight calibration approaches to improve the precision of estimates of both relative hazards and pure risks by additionally using follow-up time information available in the cohort. We develop explicit variance formulas for the weight-calibrated estimates based on influence functions. We also consider the semiparametric additive hazards model framework. Simulations show the improvement in precision by using weight calibration and confirm the consistency of variance estimators and the validity of inference based on asymptotic normality. Examples are provided using data from NIH-AARP Diet and Health Cohort Study.