Breast cancer data set used in Royston and Altman (2013)
The rotterdam data set includes 2982 primary breast cancers patients
whose data whose records were included in the Rotterdam tumor bank.
rotterdam data(cancer, package="survival")
A data frame with 2982 observations on the following 15 variables.
pidpatient identifier
yearyear of surgery
ageage at surgery
menomenopausal status (0= premenopausal, 1= postmenopausal)
sizetumor size, a factor with levels <=20 20-50 >50
gradedifferentiation grade
nodesnumber of positive lymph nodes
pgrprogesterone receptors (fmol/l)
erestrogen receptors (fmol/l)
hormonhormonal treatment (0=no, 1=yes)
chemochemotherapy
rtimedays to relapse or last follow-up
recur0= no relapse, 1= relapse
dtimedays to death or last follow-up
death0= alive, 1= dead
These data sets are used in the paper by Royston and Altman. The Rotterdam data is used to create a fitted model, and the GBSG data for validation of the model. The paper gives references for the data source.
Patrick Royston and Douglas Altman, External validation of a Cox prognostic model: principles and methods. BMC Medical Research Methodology 2013, 13:33
rfstime <- pmin(rotterdam$rtime, rotterdam$dtime)
status <- pmax(rotterdam$recur, rotterdam$death)
fit1 <- coxph(Surv(rfstime, status) ~ pspline(age) + meno + size +
pspline(nodes) + er,
data=rotterdam, subset = (nodes > 0))
# Royston and Altman used fractional polynomials for the nonlinear termsPlease choose more modern alternatives, such as Google Chrome or Mozilla Firefox.