A reproducibly simulated randomised clinical trial, for time-to-event
(survival) and imbalanced-classification examples. The two arms have a real
survival difference: the treatment arm has a lower hazard, so the
Kaplan-Meier curves separate clearly and the log-rank test is highly
significant, and - because its event times are longer - the treatment arm is
more often right-censored by the 36-month study end. age and biomarker
also affect the hazard. The data feed survival_plot() (pass time,
event and arm, or a survival::survfit object).
Format
A data frame with 300 rows and 7 variables:
- patient
Patient identifier.
- arm
Treatment arm (factor):
placeboortreatment.- age
Age in years at enrolment.
- biomarker
Standardised baseline laboratory value.
- time
Follow-up time, in months.
- event
Event indicator: 1 event observed, 0 right-censored.
- adverse_event
Rare adverse-event indicator: 1 yes, 0 no (about 10% positive).
Details
adverse_event is a deliberately rare binary safety outcome (about a 10%
base rate) that is predictable from arm, age and biomarker. It gives
the precision-recall (pr_curve_plot()), cumulative-gains (gain_plot()),
lift (lift_plot()) and calibration (calibration_plot()) demos a
genuinely imbalanced target, where those charts are most informative.
The data are synthetic, generated by data-raw/generate_datasets.R with a
fixed seed; they do not describe any real individuals.