These data come from a randomized controlled trial in which men with stage 3 or stage 4 prostate cancer were assigned to either a therapy involving estrogen (at various doses) or a placebo.
The original data has a small number of missing values. In this version, those values have been imputed with either the median value (for continuous variables) or the most common category (for categorical variables).
Stage: Tumor stageTrt: Treatment assigned (0.2 mg estrogen, 1.0 mg estrogen, 5.0 mg estrogen, placebo)Time: Time on study (months)Status: Status at end of study. One category is alive; all other categories correspond to dead, broken down by cause of death.Age: Age in yearswt: Weight index. Weight (kg) - Height (cm) + 200pf: Patient’s activity/performance level (normal activity, in bed < 50% daytime, in bed > 50% daytime, confined to bed)hx: History of cardiovascular disease (1=yes, 0=no)sbp: Systolic blood pressure (cm Hg)dbp: Diastolic blood pressure (cm Hg)ekg: Result of electrocardiogram (normal, benign, various disease indicators)hg: Serum hemoglobin (g/100mL)sz: Size of primary tumor (cm2)sg: Combined index of tumor stage and gradeap: Serum prostatic acid phosphatase (ng/mL)bm: Bone metastasis (1=yes, 0=no)Date: Calendar date patient was enrolled in studyI obtained the data from http://biostat.mc.vanderbilt.edu. The original source is
Byar DP, Green SB (1980). The choice of treatment for cancer patients based on covariate information. Bulletin du Cancer, 67:477-488.