Load the leukemia dataset.

These data are taken from Table 1.1 of [1].

The data consist of times of remission (in weeks) of two groups of leukaemia patients. Out of the 42 total patients, 21 were in a control group, and the other 21 were treated with the drug 6-mercaptopurine. Right-censoring is common in the treatment group, but there is no censoring in the control group.

Patients were observed until their leukemia symptoms relapsed or until the study ended, whichever occurred first. Each patient in the control group experienced relapse before the study ended, while 12 patients in the treatment group did not come out of remission during the study. Thus, there is heavy right-censoring in the treatment group and no right-censoring in the control group.


The leukemia data. Column descriptions:


The observed leukemia remission times.


Right-censoring indicators (0=censored, 1=event).


Group labels (control or treatment).


[1](1, 2) D. R. Cox and D. Oakes. Analysis of Survival Data. Chapman & Hall, London (1984), pp. ix+201.