A data frame contains data on recurrences of bladder cancer, used by many people to demonstrate methodology for recurrent event modeling. The data was obtained by courtesy of Ying Zhang, containing records of 118 patients from three treatment arms: 48 are from the placebo arm, 37 are from the thiotepa arm, and the rest 33 are from the pyridoxine arm.
data(bladTumor)
A data.frame
contains the following columns:
subject
patient id
time
observation time
count
cumulative number of tumors
count2
number of new tumors since last observation time
number
initial number of tumors (8=8 or more)
size
size (cm) of largest initial tumor
pyridoxine
dummy variable for pyridoxine arm
thiotepa
dummy variable for thiotepa arm
To our surprise, the two-treatment (placebo and thiotepa) subset of
the full version bladTumor
do not match the two-treatment
version blaTum
.
Byar, D. P. (1980). The Veterans administration study of chemoprophylaxis for recurrent stage I bladder tumors: Comparisons of placebo, pyridoxine, and topical thiotepa. Bladder Tumors and Other Topics in Urological Oncology, pp. 363--370. New York: Plenum.
Wellner, J. A. and Zhang, Y. (2007) Two likelihood-based semiparametric estimation methods for panel count data with covariates. Annals of Statistics, 35(5), 2106--2142.
Lu, M., Zhang, Y. and Huang, J. (2009) Semiparametric estimation methods for panel count data using monotone B-Splines. Journal of the American Statistical Association 104(487), 1060--1070.
data(bladTumor) ## Plot bladder tumor data p <- plot(with(bladTumor, PanelSurv(subject, time, count2))) print(p)