In addition, patients were excluded, in the following order, on the basis of age at diagnosis younger than 15 years or 100 years or older, unknown vital status, duplicate registration (records with identical data for site code, sex, race, date of birth, and diagnosis), unknown sex or female sex for prostate cancer, invalid sequence of dates (all combined, n = 3), or zero survival (n = 1464). We excluded patients for whom the diagnosis date was exactly the same as the date of death because we were unable to distinguish a death certificate–only case from someone who had zero survival. In all, we excluded 2.3%, 5.0%, 1.8%, and 6.3% of colorectal, lung, breast, and prostate cases, respectively. The final data set for analysis included 7661, 12 477, 8758, and 6959 patients with these cancers, respectively. This study was approved by the institutional review boards of the Centers for Disease Control and Prevention, Atlanta, Ga, and the University of Kentucky, Lexington.