Measurement error in covariates in the marginal hazards model for multivariate failure time data.

We consider measurement error in covariates in the marginal hazards model for multivariate failure time data. We explore the bias implications of normal additive measurement error without assuming a distribution for the underlying true covariate. To correct measurement-error-induced bias in the regression coefficient of the marginal model, we propose to apply the SIMEX procedure and demonstrate its large and small sample properties for both known and estimated measurement error variance.

Communicating breast cancer risk: patient perceptions of provider discussions.

This study investigated the relationship between breast cancer risk communication delivered by providers and patient knowledge, perceptions, and screening practices. Telephone interviews were conducted with 141 African American (n = 71) and white (n = 70) first-degree relatives of breast cancer patients who received medical services at 2 university medical centers in North Carolina during 1994-95. Multiple items assessed subjects' reports of discussions with providers about family history and personal risk, knowledge of breast cancer risk factors, risk perceptions, breast cancer concerns, and screening practices.